Skip to content
How it runs

From a request to a forecast, in four moves

The same loop for a client follow-up and a production bug, and the same loop whether a person or an agent does the step. Nothing here is a hand-off between tools: each move leaves the work in the state the next one expects.

Move 01

Capture, and let triage route it

Work arrives from four places and lands in one queue. Press C in the app, type /falrow create in Slack, convert a reviewed client meeting, or let your agent open the ticket itself.

  • Bug, change, feature or task, each type with its own default owner and starting stage
  • Up to 20 ordered triage rules match the title or the source and set owner and labels
  • Snooze for an hour, a day or a week, or resolve it as a duplicate
  • Templates for the tickets you open over and over
Move 02

Plan the cycle

Pull the routed work into a scheduled cycle, check capacity per person while you are doing it, and attach the milestones the roadmap is counted from.

  • Recurring schedules for the whole workspace or per project, 1 to 56 days with a cooldown
  • Up to 12 cycles planned ahead
  • Milestones with a status, an owner and target dates
  • Unfinished work rolls over after you review it, or automatically
Move 03

Build with your agent

Open the repository. The agent sends the git remote, the workspace answers with that application's plan, and the agent updates tickets as it goes.

  • plan_context matches the remote to an application and returns its stack, owners and open tickets
  • Every write carries the version it read, so a stale write is rejected rather than applied
  • Bulk edits of up to 100 tickets are all-or-nothing
  • Links, Markdown and text documents ride along on the ticket
Move 04

Measure, then forecast

The report is rebuilt from each ticket's recorded history rather than from its current state, so work that moved project, reopened or was deleted still counts where and when it really was.

  • 12 sections: cumulative flow, time in stage, lead and cycle time percentiles, aging and blocked work
  • A Monte Carlo forecast over 2,000 runs for P50, P85 and P95 dates
  • Below 4 complete weeks and 10 completions it says so instead of guessing
  • Saved reports you can share
Clients & meetings

From the client call to the cycle, without retyping

If you build for clients, the reason behind a ticket is usually a conversation. Falrow keeps the customer, the meeting and the resulting tickets linked, so the developer and the agent can both see why the work exists and who it is for.

1Bring in the meeting
Nordlys · kickoff callGranola

## Next steps

  • Add Arabic to the booking flow
  • Send staging link for sign-off by Friday
  • Quote phase two: staff scheduling
  • Ask about their hosting contract
2Review what becomes work
ProjectNordlys booking app
CustomerNordlys Hotels
Reviewed noteversion 3
Create 3 tickets
3Tickets linked both ways
NOR-218Add Arabic to the booking flow kickoff call Nordlys Hotels
NOR-219Send staging link for sign-off kickoff call Nordlys Hotels
NOR-220Quote phase two: staff scheduling kickoff call Nordlys Hotels
Three ways inImport from Granola with your own API key and a private preview, upload a Markdown or text file, or paste the notes. Each Granola meeting imports once per workspace.
No surprise ticketsUnchecked tasks, TODO and ACTION lines, and bullets under a next-steps heading are suggested, found by fixed rules rather than a model. You pick; converting again never duplicates.
A CRM that knows the workCustomers carry contact, stage and notes, and link to the applications you build for them. Open a customer and see its projects; open a ticket and see the meeting behind it.
Agent-first · 115 MCP tools

Your coding agent works from the real plan

Falrow runs its own MCP server on the same database as the app. Claude Code, Codex or any MCP client signs in once, then reads the plan for the repository it is standing in, picks up tickets and records progress, with the permissions of the person who connected it.

Claude Code~/code/client-portal connected
What should I work on in this repo?

An illustration with demo data. Tool names and behaviour are the server's own.

Connect once, per person
# your workspace's MCP endpoint
claude mcp add --transport http \
  falrow https://<your-workspace>/api/mcp

Browser sign-in with OAuth and a consent screen, or a workspace token that expires after 90 days. Plus an agent package with a development workflow skill for Claude Code and Codex.

A few of the 115 tools
plan_contextMatch the git remote to an application and return its plan
workspace_contextIdentity, team and exact counts in one compact read
search_issuesPaginated search by text, stage, owner, cycle or label
bulk_update_issuesEdit 1 to 100 tickets atomically, each at its version
convert_meeting_actionsTurn reviewed meeting actions into linked tickets
development_reportFlow, cycle time and Monte Carlo delivery forecast
Same role as the personOwner, admin, member or viewer. An agent can do exactly what the person who connected it can do, in that one workspace.
Version-checked writesEvery update sends the version it read. If a teammate changed the ticket first, nothing is written and the agent re-reads.
Scoped and revocableRead or write scope, rotating refresh tokens, and a list of connections you can revoke from the Integrations screen.
Ticket text is dataThe server tells agents to treat notes, descriptions and comments as untrusted data, never as instructions.
Why the loop holds

The rules are on the records, not on the person following them

A process that depends on everyone remembering it stops working the week someone is on holiday. These are checked by the service layer, so the app, Slack, the API and every agent get the same answer.

Stages you definedName your own stages under Triage, Backlog, Todo, In progress, In review, Done and Canceled, and limit which moves are allowed between them.
Done means somethingA project can require an owner, an estimate and closed blockers before a ticket may reach Done. The check runs wherever the move came from.
Nobody writes over anybodyVersion-checked updates for people and agents alike, and bulk edits that reject the whole batch if one ticket has moved since it was read.

Run one real cycle on it

Bring a project that already exists, not a sandbox. We set the workspace up with you and watch the first cycle through.