What it does
Salesforce Pipeline Forecast Reconciler cross-validates a Salesforce pipeline forecast against historical stage-level win rates. It produces adjusted revenue forecasts (adjusted_amount = opportunity_amount x stage_win_rate), flags high-risk and overdue deals, and outputs a full reconciliation report with per-quarter breakdowns. Stages with too few closed deals are flagged as statistically unreliable. The report can optionally be published to Google Sheets and posted to Slack. All outputs are labelled as statistical projections, never official commitments, and individual rep performance is always aggregated — no personal performance tables are ever produced. Built for RevOps and sales leadership who need an independent, deterministic check on pipeline-based forecasts.
Example prompts
- Run the full pipeline forecast reconciliation for this quarter
- Give me a summary of the current active pipeline by stage
- Calculate win rates per stage from our closed opportunities
- Flag high-risk and overdue deals in the current forecast
Tools (8)
Tools the agent exposes — your AI client calls them automatically when it needs them.
- run_full — Run the full reconciliation end-to-end: collect opportunities, calculate win rates, compute adjusted forecast, score findings, synthesize narrative, optionally publish to Sheets + Slack.
- get_pipeline_summary — Fetch the current active Salesforce pipeline and return a summary: total amount, deal count, stage breakdown, overdue deals.
- calculate_win_rates — Calculate stage-level win rates from historical closed opportunities with reliability flags.
- reconcile_forecast — Given active + historical opportunities, compute the full forecast reconciliation deterministically.
- score_findings — Given a ForecastReconciliation object, compute threshold-based findings (delta, high-risk deals, overdue deals, pipeline coverage).
- list_capabilities — List the agent's capabilities, credential slots, and guardrails.
- plan_inputs — Plan the inputs for a tool: returns questions, schema and a ready-to-edit example.
- discover_intent — Proactively clarify the user's goal before running any tool.
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.
- Salesforce Access Token · optionalSalesforce OAuth access token (SF_ACCESS_TOKEN). Required for live Salesforce data. Leave blank to use mock fixtures for testing.Get this from login.salesforce.com's account or API settings.Paste the value as a single line.Only sent to: login.salesforce.com, *.salesforce.com
- Salesforce Instance URL · optionalSalesforce instance URL, e.g. https://myorg.my.salesforce.com. Required alongside the access token for live data.Get this from *.salesforce.com's account or API settings.Paste the value as a single line.Only sent to: *.salesforce.com
- Service account JSON · optionalIn Google Analytics, find your property ID under Admin → Property Settings. Then create a service-account JSON key in Google Cloud (IAM & Admin → Service Accounts → Keys → Add key → JSON) and give that service account Viewer access to the GA4 property.Paste the full JSON of your service-account key file (not a file path). FindAgent stores it securely and gives the agent a file path to it.Only sent to: sheets.googleapis.com, oauth2.googleapis.com
- Slack Bot Token · optionalSlack bot token (xoxb-...) for posting forecast summaries to a #revenue channel.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.
