Agent catalog
Public workflow agents
Agent Ecology agents are specialized expert processes with documented inputs and outputs. They are not interchangeable chat endpoints. Pick the agent whose process matches the job you need done, then store the async job ID and reconcile the result when it completes.
How to choose
Discovery and search
Use discovery agents when users start with a query, function, habitat, strategy, or broad project context and need candidate records to review.
Synthesis and curation
Use synthesis agents when you already have source material and need summaries, grouped strategies, normalized records, or review-ready output.
Media and follow-up
Use media and follow-up agents after candidate systems are known, especially when your product needs image references, attribution, or additional evidence review.
Executive Summary
agents.executive_summary
Turns structured project, research, evaluation, or workflow notes into a concise executive-ready summary. It accepts seven named source sections, generates an overview, extracts key insights, and recommends focus areas for next steps.
Required inputs
- session_id
- A caller-provided identifier for the source session, workflow, or brief.
- sections
- Object containing the seven source section strings used for synthesis.
- sections.challenge_summary
- Core challenge, problem, opportunity, or question being summarized.
- sections.desired_outcomes
- What success should look like, including goals, criteria, or expected results.
- sections.functional_needs
- Functions, capabilities, actions, or jobs the work needs to support.
- sections.operating_context
- Relevant environment, timeline, scale, geography, organization context, or execution setting.
- sections.constraints
- Boundaries, non-negotiables, risks, policy limits, resource limits, or implementation constraints.
- sections.stakeholders
- People, teams, communities, partners, decision-makers, or affected groups.
- sections.assessment
- Current state, what is working, gaps, pain points, evaluation findings, or readiness signals.
Representative output
- job_id
- Identifier used to poll GET /v1/jobs/{job_id}.
- status
- Job state, such as queued, running, completed, or failed.
- agent_id
- The invoked agent, here agents.executive_summary.
- poll_url
- Relative polling URL for the job result.
Use after another workflow has collected and structured project, research, evaluation, or stakeholder context.
Adaptive Search Instrument
agents.adaptive_search_instrument
Runs bounded web and citation-oriented research around a focused question. It returns cited answer groups, deduplicated source cards, partial-error reporting, and a source strategy value that lets builders tune discovery for speed, breadth, or citation emphasis.
Required inputs
- query
- Focused research question or search task. Include domain, timeframe, geography, evidence expectations, and intended use when those details matter.
Representative output
- job_id
- Identifier used to poll GET /v1/jobs/{job_id}.
- status
- Job state, such as queued, running, completed, or failed.
- agent_id
- The invoked agent, here agents.adaptive_search_instrument.
- poll_url
- Relative polling URL for the job result.
Use when a workflow needs current source discovery before synthesis, review, evidence collection, or knowledge-base enrichment.
Multifunctional Search Agent
agents.multifunctional_search
Turns project context into related biological design functions, searches for biological strategies that can satisfy those functions together, and returns a narrative synthesis plus structured groups and candidate strategy records.
Required inputs
- session_id
- Caller-provided run or project identifier. Use a stable value when connecting this result to the rest of your workflow.
- context
- Project context, transcript excerpt, challenge notes, product constraints, workshop notes, or research question.
Representative output
- job_id
- Identifier used to poll GET /v1/jobs/{job_id}.
- status
- Job state, such as queued, running, completed, or failed.
- agent_id
- The invoked agent, here agents.multifunctional_search.
- poll_url
- Relative polling URL for the job result.
Use near the beginning of a larger workflow, before deeper literature review, image selection, evidence gathering, strategy distillation, or workshop synthesis.
Living Systems Search
agents.biomimicry.living_systems_search
Finds organisms and other living systems that match a name, biological function, habitat context, or strategy keyword. It returns structured candidate cards with names, descriptions, functions, strategies, ranking signals, and optional image references.
Required inputs
- query
- The organism name, function, habitat context, or strategy phrase to search for.
Representative output
- results[]
- Living-system candidate cards returned after filters and limit are applied.
- total_found
- Returned match count after filtering and limit application.
- query
- The original submitted query string.
- search_type
- The mode used for the search.
Use when a product needs candidate organisms or living systems before deeper review, synthesis, image selection, or record lookup.
Material Mapper
agents.ecoservices.material_mapper
Maps a design strategy into extracted materials, building metabolism flows, connected ecosystem services, relevant building roles, place-aware opportunity gaps, and system/role/stage lenses. It is built for early design review, educational exploration, circularity workflows, and ecosystem-service framing before a team commits to detailed engineering or procurement decisions.
Required inputs
- strategy_description
- Required natural-language description of the design strategy, system, intervention, retrofit, or concept to map. Include materials, assemblies, flows, site features, and design intent when known.
Representative output
- job_id
- Identifier used to poll GET /v1/jobs/{job_id}.
- status
- Job state, such as queued, running, completed, or failed.
- agent_id
- The invoked agent, here agents.ecoservices.material_mapper.
- poll_url
- Relative polling URL for the job result.
Use when a workflow has a building, landscape, infrastructure, or spatial design strategy and needs to understand the material flows, ecosystem-service relationships, and design roles implied by that strategy.
Expansive Biomimicry Research Agent
agents.biomimicry.expansive_research
Launches a long-running biomimicry research job that builds a broad portfolio of biological strategy records for a functional challenge. It is designed for discovery, early R&D, education, regenerative design, and downstream synthesis workflows where breadth, citations, and mechanism detail matter more than immediate lookup speed.
Required inputs
- session_id
- Caller-chosen session label for this research run. Use it for correlation and resume flows; do not treat it as a guaranteed idempotency key.
- design_challenge
- Functional challenge and operating context to research. Strong inputs describe what must be achieved, where, and under what constraints.
Representative output
- job_id
- Identifier used to poll GET /v1/jobs/{job_id}.
- status
- Job state, such as queued, running, completed, or failed.
- agent_id
- The invoked agent, here agents.biomimicry.expansive_research.
- poll_url
- Relative polling URL for the job result.
Use when a workflow needs a broad, cited portfolio of biological strategy records before filtering, synthesis, education, design review, or downstream recommendation.
Strategy Distiller Agent
agents.biomimicry.strategy_distiller
Compresses a larger set of submitted biomimicry strategy records into a smaller, reviewable set of biology-language strategy families. It preserves source_strategy_ids, organisms, citations, and mechanism nuance so downstream builders can move from synthesis back to the source records.
Required inputs
- strategies
- Array of source strategy records to synthesize.
- design_challenge
- Design or research challenge that gives the synthesis context.
Representative output
- job_id
- Identifier used to poll GET /v1/jobs/{job_id}.
- status
- Job state, such as queued, running, completed, or failed.
- agent_id
- The invoked agent, here agents.biomimicry.strategy_distiller.
- poll_url
- Relative polling URL for the job result.
Use after search, upload, or curation has produced source strategy records and the workflow needs a smaller review set without losing source links, citations, organisms, or mechanism nuance.
Taxonomy Normalizer Agent
agents.validation.taxonomy_normalizer
Normalizes messy organism, taxon, and functional-group names into reviewable workflow data. It preserves original submitted names, explains merge and keep decisions, flags ambiguous cases, and returns compact hierarchy context for downstream use.
Required inputs
- inputs.items
- Array of names to normalize. Each item should include name and may include context and source.
- inputs.items[].name
- Organism, taxon, or functional-group name.
Representative output
- job_id
- Identifier used to poll GET /v1/jobs/{job_id}.
- status
- Job state, such as queued, running, completed, failed, or cancelled.
- agent_id
- The invoked agent, here agents.validation.taxonomy_normalizer.
- poll_url
- Relative polling URL for the job result.
Use before downstream record creation, search, image selection, education, research curation, data cleanup, or knowledge-base workflows that need normalized biological names with original-name provenance.
Living Systems Curator API
agents.biomimicry.living_systems
Creates, updates, or reuses living-system records from a bounded curation task. It is useful when a workflow has identified organisms or biological systems and needs stable IDs for later search, image selection, reporting, education, product discovery, or knowledge review.
Required inputs
- inputs.task
- Bounded curation instruction. Name the biological systems and the purpose of the curation.
Representative output
- job_id
- Identifier used to poll GET /v1/jobs/{job_id}.
- status
- Job state, such as queued, running, completed, failed, or canceled.
- agent_id
- The invoked agent, here agents.biomimicry.living_systems.
- poll_url
- Relative polling URL for the job result.
Use after a workflow, extractor, spreadsheet, lesson, catalog, or reviewer has identified a bounded list of organisms or biological systems that need stable living-system IDs.
Living System Image Selector
agents.biomimicry.living_system_image_selector
Selects the best available image for a known living-system record from existing linked images and curated catalog candidates. The response preserves source, license, license URL, and attribution metadata when a suitable image is available, or returns a normal pending_collection state when image coverage still needs curation.
Required inputs
- inputs.living_system_id
- Known living-system record ID.
- inputs.living_system_name
- Common name used for display and candidate lookup.
- inputs.selection_context.context_type
- One of strategy, function, pattern, principle, or general.
- inputs.selection_context.description
- Concise explanation of what the image should illustrate.
Representative output
- job_id
- Identifier used to poll GET /v1/jobs/{job_id}.
- status
- Job state, such as queued, running, completed, failed, or canceled.
- agent_id
- The invoked agent, here agents.biomimicry.living_system_image_selector.
- poll_url
- Relative polling URL returned when the job is accepted.
Use after a living-system record has been resolved and your application needs one representative image for a page, card, report section, gallery item, lesson, or assistant response.
Living System Image Collector
agents.biomimicry.living_system_image_collector
Finds, screens, and links candidate images for a known living-system record. It is built for image coverage maintenance: callers provide a living_system_id, collection limits, and optional job metadata; the completed job returns accepted images, rejected counts, rejection reasons, provenance fields, and charge_usd.
Required inputs
- inputs.living_system_id
- Identifier of the living-system record to enrich.
Representative output
- job_id
- Identifier used to poll GET /v1/jobs/{job_id}.
- status
- Job state, such as queued, running, completed, failed, or canceled.
- agent_id
- The invoked agent, here agents.biomimicry.living_system_image_collector.
- poll_url
- Relative polling URL returned when the job is accepted.
Use after a living-system record has been resolved and image coverage is missing, weak, or needs a small reviewed expansion.