1. Working with Agentic AI: Bioinformatics Technician

How human skills and agentic skills are dynamically integrated and coordinated across bioinformatics operations and technical support

1.1. Bioinformatics Technician as an Occupation

A bioinformatics technician executes, maintains, and monitors the operational infrastructure required to process, store, and manage large-scale biological data. While bioinformatics scientists focus on developing novel algorithms and interpreting complex molecular models, the bioinformatics technician serves as the operational backbone, ensuring that routine computational pipelines run reliably, sequencing data meets stringent quality standards, biological metadata is accurately tracked, and computational resources remain available for research teams. This occupation connects wet-laboratory outputs with computational analysis environments by transforming raw sequencing instrument files and sample manifests into rigorously quality-controlled, securely stored, and properly formatted datasets ready for advanced scientific inquiry. To ensure this operational flow remains uninterrupted, the technician must understand how experimental designs, laboratory information management systems (LIMS), file system architectures, and standard operating procedures (SOPs) collectively determine the integrity and usability of biological data.

Typical responsibilities of a bioinformatics technician include:

• routine bioinformatics pipeline execution and maintenance;

• sequencing data quality control and basic processing;

• biological sample metadata and database management;

• computational resource and storage system support;

• basic data extraction and scientific collaboration support; and

• bioinformatics documentation and standard operating procedure (SOP) execution.

These responsibilities are fulfilled through distinct tasks and subtasks, each requiring one or more actions with specific skill requirements. Human skills and agentic skills both contribute to these responsibilities, but their levels and forms of involvement differ according to the responsibility, task, action, data, operational context, technical environment, and expected outcome.

1.2. Human Skills and Agentic Skills in Bioinformatics Operations

Bioinformatics operations increasingly integrate both human skills and agentic skills.

Human skills are reusable capabilities possessed and developed by bioinformatics technicians. They include operational troubleshooting, wet-lab-to-dry-lab communication, metadata curation logic, system resource judgment, quality control interpretation, procedural adherence, and technical support empathy.

Agentic skills are reusable capabilities available to AI agents through their underlying models, contextual information, instructions, constraints, tools, and computational resources. In bioinformatics operations, these skills include automated log parsing, batch quality control report generation, metadata schema validation, storage quota scanning, routine script execution, error code classification, and documentation drafting.

Both skill types contribute to the same occupational responsibilities, but their involvement varies by action. Understanding why a standardized alignment pipeline failed on a specific batch of samples relies primarily on human knowledge of recent wet-lab protocol changes and cluster node behaviors; an AI agent may then use agentic skills to parse thousands of lines of system logs, isolate the exact memory fault, and classify the error type. In metadata management, the technician first determines the required experimental variables for a new cohort, and an AI agent subsequently scans incoming spreadsheet manifests to flag missing fields or mismatched sample barcodes. Across these actions, human and agentic skills are activated sequentially or iteratively based on task requirements, with the human professional maintaining oversight and final judgment.

The relationship between these skills is not a fixed division where certain responsibilities permanently belong to humans and others to AI. Instead, human and agentic involvement shifts across tasks and between different actions within the same task.

1.3. Dynamic Human–Agentic Skill Integration and Collaboration in Bioinformatics Operations

Bioinformatics technical operations can be understood as an occupation where responsibilities are fulfilled through tasks and subtasks, tasks and subtasks are executed through actions, and actions require appropriate configurations of human and agentic skills.

An occupation provides the overall professional context. For the bioinformatics technician, this context encompasses maintaining data pipelines, ensuring sequencing data quality, managing sample metadata, supporting computational infrastructure, and facilitating data access for research scientists.

A responsibility represents an expected area of professional work or an outcome that the technician accomplishes or maintains. Responsibilities such as pipeline maintenance, quality control, and storage support each contain multiple tasks.

A task is a context-dependent unit of work used to fulfill part or all of a responsibility. When a task is too broad or complex for reliable execution, it is decomposed into smaller subtasks.

Tasks and subtasks are executed through one or more actions. Actions represent reusable and configurable operations such as triggering a daily quality control script, validating a metadata CSV file against a database schema, clearing temporary cache directories, extracting a specific gene expression matrix, or updating a software environment module.

Each action has skill requirements. These requirements describe the capabilities needed for effective and reliable execution. Depending on the action and its context, human skills, agentic skills, or an integration of both can satisfy these requirements.

The skills available for bioinformatics operations reside in a skill space containing both human skills and agentic skills. Relevant skills in this space can serve as candidate skills for executing the actions required by a particular task. A human skill in wet-lab communication, for example, can serve as a candidate for resolving an ambiguous sample label, while an agentic skill in schema validation can serve as a candidate for detecting formatting errors in the corresponding digital manifest.

Candidate skills are evaluated relative to the requirements of the action and its occupational and task context. Appropriate skills are then selected and organized into a skill configuration for execution. Depending on these requirements, a configuration may rely mainly on human skills, mainly on agentic skills, or on an integrated arrangement of both.

1.3.1. Skills Competition and Skills Collaboration

Two important relationships can occur between human skills and agentic skills when constructing a skill configuration: skills competition and skills collaboration.

Skills competition occurs when both a human skill and an agentic skill can satisfy the same or similar requirements for an action, but simultaneous application of both is unnecessary. Under a particular occupational and task context, one skill type can provide a better fit for the action than the other.

For example, both a bioinformatics technician and an AI agent can generate a summary of failed computational jobs from the previous night. When the job scheduler logs and error codes are standardized, the agentic skill provides fast and scalable execution, instantly categorizing the failures. When the summary requires interpreting whether a spike in network timeouts correlates with a known institutional IT maintenance window or a localized hardware degradation, the technician’s human skills provide the necessary contextual understanding.

The purpose of skills competition is not to establish whether human or agentic skills are generally superior. Rather, it identifies which available skill provides the better fit for a particular action under particular conditions.

Skills collaboration occurs when one skill type alone cannot effectively satisfy the requirements of a task or its actions, or when combining complementary human and agentic skills produces stronger task performance.

Collaboration does not require human and agentic skills to operate simultaneously. Instead, they are activated at different stages of action execution in a sequential, iterative, or recursive manner according to evolving task requirements.

For example, an automated quality control system flags a batch of sequencing data for abnormal GC-content distribution. An AI agent retrieves the associated library preparation logs and cross-references them with recent reagent lot numbers. The technician subsequently reviews this compiled evidence, recognizes that the anomaly coincides with the introduction of a new enzymatic kit in the wet lab, and determines that this is a systematic batch effect rather than a biological signal or sequencer failure. Based on the technician’s direction, the agent then formats an incident report and updates the metadata database to flag the affected samples for downstream normalization. Throughout this sequence, human and agentic skills are activated iteratively as task requirements evolve, while the technician directs the investigation and evaluates its outcomes.

This dynamic relationship allows bioinformatics technicians to leverage the complementary strengths of both skill types rather than relying on a permanent allocation of work.

1.3.2. Skill Configuration and Task Execution

A skill configuration specifies which human skills and agentic skills are used to execute the actions associated with a task or subtask and how those skills are coordinated.

The configuration depends on factors such as action requirements, data volume, system stability, procedural strictness, expected reliability, available computational resources, information sensitivity, downstream research consequences, and intermediate results.

For one action, an agentic skill may independently satisfy the requirements. For another, a human skill may provide the better fit. A complex task may require several configurations across multiple actions, with human and agentic skills repeatedly interacting as the task progresses.

The configuration is therefore dynamic rather than permanent. It may change when the action changes, new laboratory protocols are introduced, an agentic result fails to satisfy expected operational constraints, or human interpretation identifies a new infrastructure bottleneck.

Throughout this process, the bioinformatics technician remains the professional responsible for directing and controlling the work associated with the occupation and its responsibilities. Agentic AI provides powerful complementary capabilities that expand what the professional can monitor, validate, extract, format, automate, and document.

1.3.3. Task Performance Evaluation and Skill Space Adaptation

The performance produced through a selected skill configuration is evaluated against predefined evaluation metrics. These metrics determine whether the human skills, agentic skills, or their integrated configuration are sufficiently capable of performing the relevant task and its required actions.

Evaluation criteria depend on the work being performed. In bioinformatics operations, they include pipeline execution success rates, data integrity verification, metadata accuracy, storage utilization efficiency, query response timeliness, SOP adherence, and technical support resolution quality.

When a selected skill or skill configuration produces performance above the defined threshold, it passes the performance evaluation and is retained for future applications under appropriate conditions. Repeated successful use provides additional evidence about where that skill or configuration performs effectively.

When performance falls below the required threshold, the corresponding skill or configuration is not reused without modification. The relevant human or agentic skills may be refined or reconfigured, existing skills can be combined differently, or new human and agentic skills may be developed or constructed from scratch when the existing skill space lacks adequate capability.

For example, an AI agent is configured to automatically archive raw sequencing files older than 90 days to cold storage. However, task performance evaluation reveals that the agent occasionally archives files belonging to active, long-term longitudinal studies because it relies solely on file creation dates rather than project status metadata. The agentic skill is then refined through stricter database querying instructions, requiring the agent to verify the “project_active” flag in the LIMS before initiating any data movement. The revised skill is evaluated again, and once it satisfies the required performance criteria, it is retained. Human skills follow a corresponding development process: when a technician encounters a newly deployed containerization environment that behaves differently than previous virtual machines, the relevant troubleshooting capability is developed through hands-on experimentation and collaboration with systems administrators before its performance is evaluated through subsequent support tasks.

Refined and newly constructed skills that satisfy the required performance criteria are added to the skill space. In this way, task performance evaluation provides feedback not only for completing current work but also for continuously optimizing and expanding the available skill space.

The skill space is not constructed as an isolated collection of occupation-specific representations. Many human and agentic skills used in bioinformatics operations are reusable across occupations. Log parsing, database querying, schema validation, storage management, documentation drafting, and technical support contribute to work in general IT operations, data engineering, clinical data management, laboratory administration, and many other fields.

Reusable skills can therefore be represented once and configured differently according to the responsibilities, tasks, actions, and contexts of different occupations. This allows the skill space to serve a growing range of occupations without unnecessarily duplicating or exploding the number of skill representations. Occupational specialization is introduced through task context, action requirements, parameters, biological data sources, tools, constraints, and skill configurations rather than by creating a completely separate skill representation whenever the same underlying capability appears in another occupation.

The resulting process is adaptive:
occupational responsibility → task and subtask → actions → skill requirements → candidate human and agentic skills → skill configuration → task execution → task performance evaluation → skill refinement, reconfiguration, or construction → optimized and expanded skill space

This cycle allows human and agentic capabilities to evolve alongside the requirements of bioinformatics operations.

1.4. Essential Responsibilities of Bioinformatics Technician

1.4.1. Routine Bioinformatics Pipeline Execution and Maintenance

Routine bioinformatics pipeline execution and maintenance ensures that standardized computational workflows—such as read alignment, variant calling, or transcript quantification—run reliably on a daily or weekly basis. This responsibility includes scheduling automated jobs, monitoring execution queues, resolving standard software dependency issues, restarting interrupted processes, and ensuring that output files are correctly routed to designated project directories.

Agentic skills contribute extensively to log parsing, error code classification, automated job rescheduling, and dependency tracking. Human skills remain essential for distinguishing between transient cluster hardware failures and fundamental biological data anomalies that cause pipeline crashes, communicating with wet-lab teams regarding sample issues, and deciding when a failed pipeline requires escalation to a bioinformatics scientist for algorithmic review.

For example, an automated daily pipeline processing hundreds of genomic samples fails on a specific subset of files. An AI agent parses the standard error logs, identifies a memory allocation fault, and automatically attempts to rerun the jobs with increased resource requests. The bioinformatics technician reviews the agent’s summary and notices that the failing files all originate from a single sequencing run. The technician investigates the raw file headers and discovers that the sequencing instrument experienced a fluidics error, resulting in truncated, unalignable files. The technician instructs the agent to quarantine the corrupted files, updates the tracking database, and notifies the laboratory manager. This sequence combines agentic log monitoring and automated recovery with human operational judgment and cross-departmental communication.

1.4.2. Sequencing Data Quality Control and Basic Processing

Sequencing data quality control and basic processing verifies that raw molecular data meets the minimum technical standards required for downstream scientific analysis. This responsibility involves executing quality assessment tools, aggregating multi-sample reports, identifying adapter contamination or low-complexity anomalies, and filtering or trimming reads according to established standard operating procedures.

Agentic skills are well suited to batch execution of quality control software, aggregating thousands of individual HTML or text reports into unified dashboards, and automatically flagging samples that fall below predefined numerical thresholds. Human skills contribute to interpreting complex quality control plots, determining whether an anomaly represents a correctable technical artifact or a fundamental sample degradation, and deciding whether a batch requires complete re-sequencing.

For example, an AI agent processes a new batch of transcriptomic data, generates a unified quality control dashboard, and flags ten samples for abnormal GC-content distributions. The bioinformatics technician reviews the aggregated plots and recognizes a pattern characteristic of a specific ribosomal RNA depletion kit failure. The technician cross-references the sample manifest and confirms that the flagged samples were all processed on the same day using the same reagent lot. The technician then instructs the agent to append a specific technical warning to the metadata of those samples so that downstream scientists can apply appropriate normalization algorithms, rather than discarding the data outright.

1.4.3. Biological Sample Metadata and Database Management

Biological sample metadata and database management ensures the strict digital traceability of physical molecular samples. This responsibility includes maintaining laboratory information management systems (LIMS), validating incoming sample manifests, cross-referencing physical barcodes with digital identifiers, resolving naming inconsistencies, and enforcing data entry standards.

Agentic skills assist with schema validation, automated cross-referencing of spreadsheet inputs against database constraints, detection of duplicate identifiers, and formatting of standardized data exchange files. Human skills remain important for communicating with laboratory personnel to resolve ambiguous physical labels, understanding the experimental intent behind complex sample hierarchies, and governing the rules for metadata corrections.

For example, a research group submits a large spreadsheet of clinical sample metadata to accompany a new sequencing request. An AI agent scans the file and flags dozens of rows where the “collection_date” field violates the required ISO format or where patient IDs do not match the master registry. The agent generates a detailed error report. The bioinformatics technician reviews the report, recognizes that the submitting lab used a legacy naming convention for a specific sub-cohort, and contacts the lab manager to clarify the mapping. Once the human mapping logic is established, the technician configures the agent to automatically transform the legacy IDs into the standardized format and ingest the validated metadata into the central database.

1.4.4. Computational Resource and Storage System Support

Computational resource and storage system support maintains the digital environment required for large-scale biological data processing. This responsibility includes monitoring storage quotas, managing temporary cache directories, archiving completed project data to cold storage, managing basic user access permissions, and reporting hardware utilization to systems administrators.

Agentic skills contribute to continuous storage scanning, identification of orphaned temporary files, automated archiving based on file age and project status, and generation of resource utilization reports. Human skills define data retention policies, evaluate the scientific value of historical datasets before deletion, handle complex cross-departmental access requests, and coordinate with institutional IT teams during hardware upgrades.

For example, a high-performance computing cluster approaches its storage capacity limit, threatening to halt active sequencing pipelines. An AI agent scans the file system and identifies several terabytes of intermediate alignment files belonging to projects marked as “completed” in the database. The agent prepares a deletion script. The bioinformatics technician reviews the list and identifies that one of the “completed” projects is actually scheduled for a secondary re-analysis phase next month. The technician modifies the agent’s instructions to exclude that specific directory, authorizes the deletion of the remaining orphaned files, and updates the project tracking system to prevent future automated sweeps from targeting the active re-analysis data.

1.4.5. Basic Data Extraction and Scientific Collaboration Support

Basic data extraction and scientific collaboration support provides research scientists with the specific, formatted data subsets they require for advanced modeling and publication. This responsibility involves writing and executing standard query scripts, extracting specific gene expression matrices, formatting variant call files (VCFs) for external databases, and fulfilling routine data requests from biological researchers.

Agentic skills retrieve data from complex directory structures, execute standard SQL or bash queries, format output files to meet strict external repository requirements, and generate basic descriptive summaries of the extracted subsets. Human skills evaluate the scientists’ actual analytical needs, clarify ambiguous data requests, ensure that the extracted subsets include the correct control samples, and verify that the final data package is scientifically coherent.

For example, a bioinformatics scientist requests “all differentially expressed genes from the recent stress experiment” to build a regulatory network model. The bioinformatics technician recognizes that the scientist’s request lacks the necessary statistical thresholds and control group specifications. The technician clarifies the required fold-change and p-value cutoffs with the scientist. An AI agent then executes the customized query across the processed data warehouse, extracts the matching gene lists, and formats them into the specific matrix structure required by the scientist’s network analysis software. The technician verifies that the control samples are correctly represented in the matrix before delivering the package.

1.4.6. Bioinformatics Documentation and Standard Operating Procedure (SOP) Execution

Bioinformatics documentation and standard operating procedure (SOP) execution ensures that computational methods are reproducible, transparent, and accessible to new team members. This responsibility includes maintaining pipeline user guides, updating software environment configurations, documenting troubleshooting steps for common errors, and ensuring that all operational tasks strictly adhere to approved laboratory and computational SOPs.

Agentic skills assist with scraping code repositories for recent changes, drafting initial update notes for documentation, checking for broken links or deprecated commands in existing guides, and verifying that executed scripts match the version control hashes specified in the SOP. Human skills evaluate the clarity and accuracy of the documentation, ensure that SOPs reflect the actual realities of the wet-lab-to-dry-lab workflow, and write nuanced troubleshooting guides based on experiential knowledge of system quirks.

For example, the core bioinformatics pipeline is updated to a new major version, requiring changes to the laboratory’s SOP. An AI agent analyzes the software release notes and the git commit history, generating a draft list of changed parameters and deprecated commands. The bioinformatics technician reviews the draft and realizes that a subtle change in the default threading behavior will cause memory overflows on the laboratory’s older compute nodes. The technician manually adds a specific workaround and environment variable requirement to the updated SOP, instructs the agent to format the final document, and tests the new SOP step-by-step to ensure a junior technician could execute it without errors.

1.5. Changing Human and Agentic Involvement Across Bioinformatics Technician Responsibilities

Human skills and agentic skills are involved throughout bioinformatics operations, but their relative involvement differs across responsibilities and changes during task execution.

These involvement levels are not permanent allocations. A single responsibility may contain actions where human and agentic skills compete as alternative capabilities and other actions where they collaborate sequentially, iteratively, or recursively.

The practical objective is to construct skill configurations that use the most suitable available capabilities for each part of the work and revise those configurations when task performance evaluation shows that another arrangement performs more effectively or reliably.

1.6. Working as a Bioinformatics Technician with Agentic AI

Agentic AI is becoming an increasingly powerful component of bioinformatics operations. Bioinformatics technicians should therefore adopt and integrate AI agents as complementary participants in professional workflows rather than treating them only as occasional tools for generating summaries, parsing logs, or formatting data tables.

This shift does not reduce the importance of operational expertise and biological data stewardship. Human professionals remain responsible for the occupation and its corresponding responsibilities. They understand experimental contexts, define data quality standards, interpret system anomalies, determine appropriate metadata structures, evaluate the scientific value of stored data, communicate with wet-lab and research teams, control consequential infrastructure changes, evaluate task performance, and decide how human and agentic skills are configured and improved.

At the same time, agentic skills greatly expand the volume and variety of operational work that can be managed. AI agents retrieve and organize massive volumes of system logs, generate and aggregate quality control reports, validate complex metadata schemas, scan distributed storage environments, execute routine data extraction queries, and synthesize documentation updates at a scale difficult to achieve through direct human effort alone.

Strong bioinformatics operational practice is therefore not based on maximizing human work or agentic work independently. It is based on finding appropriate configurations of human skills and agentic skills for the responsibilities, tasks, subtasks, and actions being performed.

Where a human skill and an agentic skill can independently perform the same action, skills competition identifies which is better suited to the current context. Where work requires complementary capabilities, skills collaboration results in human and agentic skills being activated sequentially, iteratively, or recursively to achieve stronger task performance than either skill type achieves alone.

Task performance evaluation then determines whether selected skills and configurations satisfy predefined expectations. Successful skills are retained and reused, while inadequate skills are refined, reconfigured, or newly developed. The resulting capabilities return to an increasingly useful skill space that supports bioinformatics operations and, where capabilities are reusable, other occupations as well.

For a bioinformatics technician, working effectively with agentic AI means treating AI as a powerful complementary capability integrated into everyday professional routines while maintaining human control of occupational responsibilities. Through appropriate skill selection, competition, collaboration, evaluation, and continuous improvement, human professionals and agentic AI work together to achieve bioinformatics operations that are more efficient, scalable, reliable, reproducible, and fundamentally supportive of molecular research.