All case studies

Architecting the agentic
layer of an AI team brain

Role
CTO & Lead Architect
Client
Commind — collaborative AI knowledge platform
Scope
The agentic layer
Outcome
4 agentic systems — knowledge, meetings & the web

Commind is a collaborative AI knowledge platform — an AI "team brain." It began from a multi-agent orchestration mandate and grew into a production system where agentic workflows plan, use tools, and act autonomously across a team's knowledge, meetings, and the web.

I came on as CTO and Lead Architect and designed the agentic layer: tool-using research agents, an autonomous meeting-to-action pipeline, and intent-routed retrieval — along with the engineering judgment to know when not to use an agent.

4 systems
agentic workflows spanning knowledge, meetings, and the web — each one built to plan, use tools, and act, with guardrails wired in by design.

The agentic systems I architected

Built / in build

1 · Deep Research — a planner–executor loop

Decomposes a topic into sub-queries, runs multi-query web searches through a tool API, cross-references sources, and synthesizes a structured, cited report. Streams a transparent research trail — plan, search, cross-reference, synthesize — and degrades gracefully, returning partial findings on timeout rather than failing outright.

Built / in build

2 · Meeting Intelligence — perceive → reason → act

Autonomously ingests Teams transcripts via a delegated Graph API, summarizes them, extracts action items, resolves assignees against meeting-participant scope with close-match logic, and pushes tasks into Planner, To Do, Jira, and Linear. Cross-tool identity resolution maps participants to tracker user IDs.

Built / in build

3 · Intent-routed retrieval orchestration

The RAG reasoning layer: Query → Understand → Expand → Hybrid Retrieve → Rerank → Assemble → Generate. Classifies query intent — factual, exploratory, document-finding, expertise-location, temporal — to route strategy per query, blending dense (HNSW), sparse (BM25), and metadata filtering. Confidence thresholds and citation enforcement act as generation guardrails.

In active buildout

4 · Stateful conversational RAG agents

Document and presentation agents that maintain outline and source-ID state, recognize structural operations (add, reorder, modify), re-query the knowledge base on demand, and explain their own reasoning — answering "why this source?" with a relevance justification.


Signature architectural judgment

  • Agentic when warranted, deterministic when better. I chose synchronous, debuggable pipelines and a one-report-per-conversation state machine over open-ended agent loops, and deliberately deferred a full agent/MCP layer until the RAG foundation was solid. The hardest call in agentic engineering is usually the one against using an agent.
  • Guardrails by design. An ambiguous assignee results in no action taken, rather than a confident wrong one. Custom agents are scoped strictly to internal knowledge. Confidence gates and mandatory citations sit between retrieval and generation.
  • Least-privilege by default. Delegated, user-controlled OAuth (PKCE) means agents act per user — never through admin service accounts. The system can only ever do what the person it's acting for could do.
The hardest call in agentic engineering is usually the one against using an agent.

Capabilities demonstrated

Multi-agent orchestration Planner–executor design Perceive–reason–act pipelines Tool-use integration (Graph API, task managers, web & vector APIs) Hybrid RAG & retrieval routing Conversation state & lifecycle design Guardrails, scoping & failure handling Agentic-vs-deterministic trade-off judgment

Have a similar challenge?

If you're building an agentic layer that has to plan, use tools, and act autonomously — safely, and with the judgment to know where an agent doesn't belong — let's talk.

Get in touch →