Documentation Menu

Core Concepts

The building blocks you need to understand the Birk ecosystem and how autonomous agents work.

01Agents

Autonomous AI units. They do more than answer a question; they reason, plan, and take action toward a defined goal. Each agent starts with a persona tailored to a specific area of expertise.

Agent Execution Loop (ReAct Pattern)
PlanBreak the goal into substeps
ActCall tools, run APIs
ObserveRead and evaluate the result
ReflectDid it meet the goal? Repeat
NOTE

A traditional LLM produces a one-off answer. A Birk Agent repeats this loop on its own until the goal is satisfied without requiring human intervention.

02Models & Open Source

Birk is built on open-source and open-weight models. Each model is selected by task type, can be fine-tuned, and runs entirely inside your own infrastructure. Your data never leaves your network.

ModelFoundationUse CaseFine-tune
Birk-FastOpen-weight LLMLow-latency classification, summarization, translationOptional
Birk-Agent-LightOpen-weight LLMTool-calling, multi-step tasks, code analysisRecommended
Birk-Agent-HeavyOpen-weight LLMComplex orchestration, long context, critical decisionsRecommended
Why Open Source?
  • -Data sovereignty: Models run on your servers; no data leaves your environment.
  • -Customization: Fine-tune with your industry data to achieve domain-specific performance.
  • -No vendor lock-in: Changing the model does not mean changing the pipeline.

03Tools & Connectors

Capabilities that let agents interact with the outside world. An agent cannot produce enterprise data by itself; it triggers tools to retrieve data or perform an action through function calling. Connectors are ready integration points for your enterprise systems.

Tool Name (Tool ID)ParametersPurpose
execute_sql{ query: string }Runs a read-only query against a PostgreSQL database.
read_local_file{ path: string }Reads log or configuration files on the server.
send_slack_alert{ channel: string, msg: string }Sends an incident or report notification to a team channel.
PostgreSQL
Database
MySQL
Database
REST API
HTTP
GraphQL
HTTP
Slack
Communication
Microsoft Teams
Communication
S3 / MinIO
Storage
JIRA
Project

04Pipeline & Orchestration

Splitting complex tasks into smaller pieces and processing them across multiple agents sequentially or in parallel. The orchestrator agent distributes the work, worker agents produce the solution, and every step remains observable, repeatable, and independently testable.

Example: Data Analysis and Reporting Pipeline
User Request

Analyze the sales decline over the last 30 days, find possible causes, and report back.

Orchestrator Agent
Plan and distribute

Splits the request into subtasks, selects which agents should run in parallel, and waits for results.

Parallel workers
Data Agent

Runs SQL queries and extracts sales and customer data for the period.

Log Agent

Scans error, outage, campaign, and integration logs.

Analysis Agent

Compares findings and flags anomalies and likely causal relationships.

Merge results
Synthesis & Report Agent
Combine and validate

Resolves contradictions across parallel agent outputs, links sources, and turns everything into one report.

Deliver
Final Output
Summary, evidence, recommended actions, and traceable task history
Sequential

Steps run in order. The output of the previous step becomes the input of the next.

Parallel (Fan-out)

Independent tasks are distributed to different agents at the same time and then merged.

Conditional

Flow routes to different branches based on the output of a step.

05Memory & Context

Defines how far back an agent can remember. The system uses dynamic context management and RAG to avoid hitting the LLM token limit.

Short-Term (Session Memory)
  • Keeps only the messages in the active chat session.
  • Deleted when the operation ends.
  • Added directly to the LLM context window.
Long-Term (Vector DB / RAG)
  • All enterprise documents, past projects, and rules.
  • Persistent and stored encrypted.
  • The agent retrieves and reads only the part it needs at runtime.

06Guardrails & System Instructions

Guardrails constrain model behavior, while system prompts define the model's role, style, and operating instructions.

agent_config.yaml
# Model Character
system_prompt: |
You are a senior DevOps engineer.
Speak only with confirmed technical evidence.
Never assume. If you do not know, say "I do not know."

# Guardrails (Zero-Trust)
guardrails:
- type: "block_sql_mutation"
action: "Reject DROP, DELETE, UPDATE, and INSERT commands."
- type: "pii_filter"
action: "If output contains email or national ID data, mask it (***)."

07Workspace & Environment Management

Every project lives inside a workspace. A workspace brings agents, tools, connectors, memory pools, and environment variables under one roof. Environments such as dev, staging, and prod run isolated from each other.

briq-workspace.yaml
workspace: my-enterprise-project
environment: production

agents:
- birk-agent-heavy # Orchestrator
- birk-agent-light # Worker agents

connectors:
- type: postgresql
host: ${{DB_HOST}} # From environment variable
- type: slack
webhook: ${{SLACK_WEBHOOK}}

memory:
vector_store: local # or 'managed'
retention: 90d
Development

Fast iteration. Mock connectors and smaller model variants are used.

Staging

Real data sources, isolated network. The final validation point before production.

Production

Full isolation, audit logs enabled, guardrails required. Deployed with rollback support.

08Monitoring & Observability

Every agent action, tool call, and model decision is logged in an observable way. End-to-end observability supports enterprise audit, debugging, and performance optimization.

Trace Log — Pipeline #28472024-01-15 14:32:07 UTC
[14:32:07] ORCH Request received → split into 2 subtasks
[14:32:08] AGENT db_analyst → execute_sql called (342ms)
[14:32:08] AGENT log_reader → read_local_file called (128ms)
[14:32:09] GUARD pii_filter → 2 fields masked (email)
[14:32:10] SYNTH Synthesis completed → report created
[14:32:10] DONE Total: 3.2s | Tokens: 4,812 | Cost: ~$0.003
Trace & Span

Every pipeline run is stored as a trace, and every agent step as a span. OpenTelemetry compatible.

Audit Log

Who queried what data, when, with which agent - a complete audit trail with immutable records.

Architecture in Essence

A high-level view of how all components work together.

Continuous Governance (Guardrails)
End-to-End Monitoring (Observable)
Orchestration & WorkflowThe main controller that manages agents, tools, and memory.
Agent (Model)Reasons, plans, and decides.
Tools & ConnectorsThe physical hands that touch systems.
MemoryShort- and long-term enterprise knowledge.