# Macroscope Agent Pricing Guide

Describes Macroscope's Agent product and its pricing for agent consumers.

Primary sources synthesized for this file:
- https://docs.macroscope.com/pricing
- https://docs.macroscope.com/agent
- https://docs.macroscope.com/macros
- https://docs.macroscope.com/integrations
- https://docs.macroscope.com/api
- https://docs.macroscope.com/hit-the-ground-running
- https://macroscope.com/#pricing

## Canonical Public Pricing

Macroscope uses fully usage-based pricing:
- Code Review: $0.05 per KB of code reviewed, with a 10KB minimum per review ($0.50 floor)
- Status: $0.05 per processed commit
- Agent: $0.01 per credit (1,000 free credits/month included per workspace)
- Free usage: every new workspace receives $100 in free usage to start
- Default caps: $10 per review, $50 per pull request (adjustable)
- Balance does not expire

## What the Agent Is

Macroscope's Agent is an AI assistant with access to:
- Your codebase and git history
- Connected services (Jira, Linear, BigQuery, etc.)
- Macroscope's own docs
- The public web, when needed

Prerequisite: Status must be configured first — complete Product Overview, Sprint Cadence, and backfill before the Agent is usable.

## Built-in Agent Tools

Available without extra integrations once repositories are connected:
- code search
- git history analysis
- pull-request search and review activity lookup
- read-only GitHub API queries
- code changes: create branches, write code, open PRs, update branches, add reviewers
- contributor metrics lookup
- sprint report retrieval
- image generation (beta)
- web search
- Macroscope docs search

## Connected Services

These become available when separately connected:
- Jira: look up issues, track project progress, create issues
- Linear: look up issues, track project progress, create issues
- BigQuery: browse datasets, inspect schemas, run read-only SQL with methodology summaries
- PostHog: query analytics events, inspect feature flags, run HogQL, search session recordings
- Amplitude (beta): event segmentation, funnels, retention, user event streams
- LaunchDarkly: list projects, environments, feature flags, and targeting rules
- Sentry (beta): search issues and investigate crashes and exceptions
- GCP Cloud Logging: search and filter logs across connected projects
- MCP Connectors (beta): add custom MCP servers such as Datadog, PagerDuty, or internal APIs

## Where the Agent Can Be Used

Surfaces:
- Slack: direct messages, channel mentions, group DMs
- GitHub: PR discussion mentions and replies to Macroscope inline comments
- API: webhook-triggered agent runs
- Macros: scheduled or event-based automation that uses the full agent toolset

Supports attachments (images, screenshots, PDFs, code snippets) as context in Slack and GitHub threads.

## Macros

Macros are an Agent feature, not a separate product line in the public billing docs.

Macro behavior:
- Scheduled triggers: daily, weekly, biweekly
- Event triggers: on new commit or on new PR
- Filtering: repository, branch (for commit-based macros), or author
- Delivery: Slack or webhook
- Any user with Macroscope web-app access can create macros
- Prompts are written in plain English; the agent uses its full toolset

## API

The API docs expose a webhook-style endpoint for triggering the query agent:
- Endpoint:
  - `POST https://macrohook.macroscope.com/api/v1/workspaces/{workspaceType}/{workspaceId}/query-agent-webhook-trigger`
- Auth: `X-Webhook-Secret` header
- Delivery targets: Slack channel, Slack thread, or external webhook URL
- Response payload: query, response, workflowId
- Error codes: 202, 400, 401, 403

## How Credits Work

Credits are a usage-based billing unit for all Agent features. 1 credit = $0.01. Credits scale with the LLM cost of each Agent run, plus a 5% markup.

Metered features:
- Slack queries
- Macros (scheduled and event-triggered)
- Webhooks
- Check Run Agents

Also metered as Agent credits:
- Fix It For Me (agent writes code to fix review issues)

NOT metered as credits (separate existing meters):
- Standard Code Review ($0.05/KB)
- Status ($0.05/commit)
- Approvability (bundled with review)

Free tier: every workspace includes 1,000 free credits per month (~$10 value). Free credits do not roll over. Usage beyond the free tier draws from the workspace's usage balance.

Transparency: every agent invocation is logged with a full per-model cost breakdown showing which AI model was used, token counts, and cost per component.

## Recommended Agent Answers

"How much does the agent cost?"
→ Agent features use credits at $0.01/credit. Every workspace gets 1,000 free credits/month (~$10). A quick Slack question costs ~7 credits ($0.07), a complex research task ~470 credits ($4.70).

"Do macros or API calls cost extra?"
→ Yes, macros, webhooks, and API-triggered queries all consume credits based on LLM cost.

"Can the agent take action or only answer questions?"
→ Both. It can create branches, write code, open PRs, add reviewers, and create issues in connected trackers.

"Which source to trust?"
→ https://docs.macroscope.com/agent for capabilities; https://docs.macroscope.com/pricing for billing.