Agentic Chat
Agentic Chat is an AI workspace combining document search, long-term memory, web research, and OAuth-connected apps for context-aware action.
Overview
Agentic Chat is built around the idea that a good AI response depends on what context you give it. Before the model sees a message, the system decides what to pull in — past conversation memory, relevant document chunks, a live web search, or the content of a URL — and assembles that into the prompt automatically.
Agentic Chat is built around the idea that a good AI response depends on what context you give it. Before the model sees a message, the system decides what to pull in — past conversation memory, relevant document chunks, a live web search, or the content of a URL — and assembles that into the prompt automatically.
From there, a LangGraph orchestrator takes over. It runs a planner, an agent, and a tool execution loop, deciding at each step whether to call a tool or return a response. The agent can connect to Gmail, Google Calendar, Drive, Docs, Sheets, Slack, Notion, GitHub, and Linear through Composio. Any action that writes, sends, or deletes something pauses and asks for explicit approval before it runs.
The stack is Next.js, React, PostgreSQL with pgvector for vector search, Prisma, Better Auth for Google sign-in, and UploadThing for file storage. Users can bring their own OpenAI key — it's encrypted at rest and never sent to the client. LangSmith traces every step of the graph.
How It Was Built
The main technical choices behind the product, from system design to the parts that make it work day to day.
- Built the LangGraph orchestrator from scratch: a planner node that breaks down the request, a supervisor agent that decides what to do, and a tool node that executes — all wired in a loop with PostgreSQL checkpointing so the conversation can resume after an approval interrupt.
- Built the document pipeline end-to-end: file upload via UploadThing, parsing for PDF, DOCX, XLS, and CSV, 800-token semantic chunking, OpenAI embeddings stored in pgvector, hybrid retrieval, and Cohere reranking to surface the most relevant chunks.
- Built the LangGraph orchestrator from scratch: a planner node that breaks down the request, a supervisor agent that decides what to do, and a tool node that executes — all wired in a loop with PostgreSQL checkpointing so the conversation can resume after an approval interrupt.
- Built the document pipeline end-to-end: file upload via UploadThing, parsing for PDF, DOCX, XLS, and CSV, 800-token semantic chunking, OpenAI embeddings stored in pgvector, hybrid retrieval, and Cohere reranking to surface the most relevant chunks.
- Integrated Composio to load each user's connected tools at runtime based on their OAuth accounts. Built the connect, callback, and status routes, plus a dangerous-action allowlist and a verb-based detector that together catch write operations and route them through an approval card before execution.
- Built the BYOK flow: AES-256-GCM encryption of the user's API key on save, and a server-side proxy that decrypts and forwards it to OpenAI so the plaintext key never touches the client.
- Wired SSE streaming from LangGraph's event stream to the client: token chunks, tool progress updates, approval request events, and planning steps all stream in real time with full abort support.
Impact
- Semantic cache with pgvector similarity search reuses prior answers for repeated or near-identical queries, avoiding redundant embedding and generation calls when context matches.
- Composio replaced per-service OAuth plumbing with one integration covering 9 toolkits and 94 essential actions (Gmail, Calendar, Drive, Docs, Sheets, Slack, Notion, GitHub, Linear).
- Semantic cache with pgvector similarity search reuses prior answers for repeated or near-identical queries, avoiding redundant embedding and generation calls when context matches.
- Composio replaced per-service OAuth plumbing with one integration covering 9 toolkits and 94 essential actions (Gmail, Calendar, Drive, Docs, Sheets, Slack, Notion, GitHub, Linear).
- Approval cards gate every write/send/delete action the agent proposes, so users confirm the exact operation before anything is executed.
- BYOK lets teams use their existing OpenAI contracts without sharing plaintext keys with the product.
Highlights
- LangGraph loop with PostgreSQL checkpointing keeps conversation state across approval interrupts — the agent picks up exactly where it left off.
- 3-tier web scraping (Readability → Firecrawl → Jina Reader) means the agent can read most pages, including JS-rendered ones, without a browser.
- LangGraph loop with PostgreSQL checkpointing keeps conversation state across approval interrupts — the agent picks up exactly where it left off.
- 3-tier web scraping (Readability → Firecrawl → Jina Reader) means the agent can read most pages, including JS-rendered ones, without a browser.
- Two-layer safety for Composio actions: an explicit allowlist of dangerous slugs, plus a verb detector as a fallback — so new actions don't silently bypass approval.
Tech Stack
More Projects
Additional work across AI products, developer tooling, and full-stack systems.
Bonkers by Foyer
Creative production system built at Foyer Tech — led the v2→v3 rebuild with reusable templates, multi-model routing, and faster repeat workflows for high-quality visual asset creation.
Fieldcraft
A careful Chrome extension copilot that reads the open job tab, evaluates fit against your profile, researches the company, and drafts truthful answers for review before any form is filled. It never auto-submits.
Inkdown
Markdown editor and sharing platform with folders, live preview, and public links.