What it does
Jira Team Velocity Forecaster fetches the last 12 completed sprints from Jira, filters outlier sprints (velocity 0 or over 3x average), runs a 10,000-iteration Monte Carlo simulation, and produces P50/P80/P95 delivery date confidence intervals. Results are always labeled as statistical projections, never commitments. Optionally creates a Notion forecast page and sends a Slack summary to an engineering-leadership channel. Ships with deterministic mock data so CI and demos require no credentials. Built for engineering leaders and project managers who want realistic, statistically grounded delivery estimates instead of single-point sprint guesses.
Example prompts
- Forecast delivery for PROJ with 120 story points remaining
- Run the full velocity forecast and post it to Notion and Slack
- What's our P80 delivery date confidence interval this sprint?
- Analyze our last 12 sprints for velocity trends
Tools (8)
Tools the agent exposes — your AI client calls them automatically when it needs them.
- run_full — Run the agent end-to-end: fetch Jira sprint history, run Monte Carlo velocity forecast, generate LLM summary, optionally post to Notion and Slack.
- analyze_velocity — Given raw sprint data, compute velocity statistics and Monte Carlo delivery forecast deterministically (no LLM, no network).
- forecast_delivery — Run Monte Carlo simulation from a velocity distribution to produce P50/P80/P95 delivery dates.
- create_notion_report — Create a Notion page with the velocity forecast report.
- send_slack_summary — Post a velocity forecast summary to a Slack channel.
- list_capabilities — List the agent's static capabilities and credential slots.
- plan_inputs — Plan/brainstorm the inputs for a tool: returns questions, schema, and a ready-to-edit example.
- discover_intent — Proactive intent discovery: state a goal, get clarifying questions and a proposed input before running.
What you'll need to connect
This agent will ask you for the following. You enter them when you connect — they're encrypted and never shared with the creator.
- Jira API Token · optionalJira API token for fetching sprint data. Leave blank to use mock data.Get this from *.atlassian.net's account or API settings.Paste the value as a single line.Only sent to: *.atlassian.net
- Jira Email · optionalEmail address associated with your Jira account, used with the API token for Basic auth.Get this from *.atlassian.net's account or API settings.Paste the value as a single line.Only sent to: *.atlassian.net
- Jira Domain · optionalYour Jira Cloud domain (e.g. yourcompany.atlassian.net). Do not include https://.Get this from *.atlassian.net's account or API settings.Paste the value as a single line.Only sent to: *.atlassian.net
- Notion API Key · optionalOptional. Notion integration token for creating forecast report pages.Create an internal integration in Notion (notion.so/my-integrations) and copy its secret, then share the relevant pages with that integration.Paste the value as a single line.Only sent to: api.notion.com
- Notion Parent Page ID · optionalThe Notion page ID where forecast reports will be created as sub-pages.Create an internal integration in Notion (notion.so/my-integrations) and copy its secret, then share the relevant pages with that integration.Paste the value as a single line.Only sent to: api.notion.com
- Slack Bot Token · optionalOptional. Slack bot OAuth token for posting forecast summaries. Requires chat:write scope.Create a Slack app (api.slack.com/apps), add the scopes the agent needs, install it to your workspace, and copy the bot/user token.Paste the value as a single line.Only sent to: slack.com
- Anthropic API Key · optionalOptional. Leave blank on a sampling-capable client to use the host model with no key.Create a key on the Anthropic Console API keys page (console.anthropic.com → API keys).Paste the value as a single line.Only sent to: api.anthropic.com
How you're protected
FindAgent runs these safety checks on every agent automatically. They're always on and can't be turned off.
- Prompt-injection scanning
Every request is checked for known prompt-injection and jailbreak attempts before the agent runs. This is always on.
- Secret-leak scanning
Every response is scanned for leaked API keys, tokens, and other secrets before it reaches you. This is always on.
