Skip to content

The multi-agent platform for engineering teams.

Crewstack turns a Work Item into a pull request. An Orchestrator agent refines the scope with you, delegates execution to specialist agents in real sandboxes with real GitHub access, and brings the result back for your review.

crewstackCR-184

Reduce auth round-trips on the dashboard load

In refinement·feat/session-bootstrap

Dashboard feels slow on load. Auth seems to be the bottleneck — needs to be faster without breaking the existing client.

Scope

Trace the four sequential auth calls fired on /dashboard mount — session, profile, prefs, and feature flags. Coalesce them into a single batched endpoint behind /session/bootstrap that preserves the public client API surface.

To be defined with the Planner.

Acceptance

  • p95 TTFB ≤ 180ms (currently 540ms)
  • no change to public client signatures
  • response cached per-user for 60s with prefs invalidation
5 agents

Planner

Refining scope with you

Files changed

    How it works

    From a sentence to a merged PR.

    The same loop a senior engineer runs — scope, delegate, review, ship — running on a contracted runtime that your admins control.

    01.

    Describe the work

    Open a Work Item, paste a one-line ask. The Orchestrator agent reads your repo, asks the questions a teammate would, and writes the scope back into the Work Item Document — with the right files, the right references, the right acceptance criteria.

    Work Item · CR-184
    crewstackCR-184

    Reduce auth round-trips on the dashboard load

    In refinement·assigned toOrchestrator

    Scope

    Trace the four sequential auth calls on /dashboard mount. Coalesce into a single batched endpoint behind /session/bootstrap. Keep the existing client API.

    Acceptance

    • p95 dashboard TTFB ≤ 180ms (currently 540ms)
    • no change to public client signatures
    02.

    Agents execute

    Specialist roles — Planner, Code Writer, Code Reviewer, Docs Writer — pick up the work in real sandboxes with real GitHub access. Each role runs under a Policy Bundle your admins control. The delegation tree is visible while it runs.

    CR-184
    Agent Treerunning
    • Orchestratorplanning the split
    • Planner3 subtasks proposed
    • Code Writerediting api/session/bootstrap.ts
    • Code Reviewerwaiting on writer
    • Docs Writerqueued
    Running in sandbox sb-9af2
    03.

    Review the PR

    Crewstack opens the pull request on your repo and links it to the Work Item. You review on GitHub the way you always have — comments, requested changes, suggested edits — and the agent responds.

    Pull Request
    Linked to CR-184
    Coalesce auth round-trips into /session/bootstrap

    crewstack/webPR-482 opened byCode Writer

    feat/session-bootstrap+184 −623 files
    • 11:02priyarequested changes on api/session/bootstrap.ts:42
    • 11:14Code Writeraddressed: switched batch reducer to Promise.all
    • 11:18priyaapproved
    04.

    Ship

    Merge the PR. Crewstack flips the Work Item to done automatically and the Orchestrator closes anything outstanding. The whole loop is recorded — tool calls, credential releases, and every state transition.

    Lifecycle · transition
    crewstackCR-184

    Reduce auth round-trips on the dashboard load

    In reviewDone
    • 11:21GitHubGitHubmerged PR-482 into main
    • 11:21Orchestratorclosed Work Item — In review → Done

    Recorded: 47 tool calls · 3 credential releases · 9 state transitions

    The substrate

    An engineering platform, not a chat session.

    The competitors orchestrate sessions in vendor-owned workspaces with opaque runtimes. Crewstack is built contract-first so a CTO can actually deploy it.

    Admins decide what agents can do

    Every agent role runs under permissions your admins control — what tools it can call, what files it can touch, what credentials it can ask for. Project owners can narrow further; they can never widen.

    Real sandboxes, not chat boxes

    Agents run inside real sandboxed workspaces with your code, your dependencies, and your tooling installed. Same environment your engineers would use. Not a chat surface pretending to have a terminal.

    Your credentials never reach the LLM

    Secrets are encrypted at rest, fetched just-in-time inside the sandbox, and never appear in any prompt sent to a model. Every release is logged with the agent, the tool, and the reason.

    Lifecycle tied to your real artifacts

    When a Work Item produces a pull request, the Work Item and the PR stay linked. Merging the PR flips the Work Item to done automatically. Your tracking surface and your engineering surface stop drifting apart.

    External context

    Wired into the work your team already does

    Agents are only as good as the context they can pull. 17 providers — GitHub, Linear, Slack, Jira, Sentry, GitLab, and more — wire them into your real stack as a unified set of tools. Events route back into the Work Item automatically; agents react to what's happening across your stack.

    Compatible with
    GitHubLinearSlackJiraSentryGitLabNotionStripeVercel+ 8 more providers

    Agents read your codebase and docs

    Your code, your docs, your tickets, your PDFs — searchable by the agents through a permission-aware retrieval layer. Agents only see what they're allowed to see, scoped per query, per role, per project.

    Encode your conventions as Skills

    Skills are reusable instruction fragments scoped to your org, workspace, project, or a single agent. Use them to teach agents your patterns, your style, your guardrails — without forking templates or hardcoding policies.

    Agent-written knowledge, kept

    Agents produce research notes, design memos, and summaries as they work. Those land as searchable artifacts attached to the Work Item. Tomorrow's planning question can answer itself from yesterday's exploration.

    Who this is for

    Built for engineering teams that ship every day.

    • 01.

      Engineering managers

      Teams of 5–50 shipping product weekly who want a sharper answer to “what should we delegate?” than a chat tab.

    • 02.

      Technical founders

      Solo or small founding teams who want a senior engineer on tap for work that isn't worth a senior hire yet.

    • 03.

      CTOs evaluating AI infra

      Leaders who need an audit trail, an admin-controlled policy surface, and a runtime that doesn't change under them.

    Not built for: non-technical buyers, chat-assistant shoppers, vibe-coders looking for an AI pair, or anyone shopping for a Jira replacement.

    Start

    See it work on your codebase.

    We'll set up a sandbox against your repo and walk through a Work Item end to end. About 30 minutes. Goes directly to the founder.