Skip to content

How Buzz’s scores are calculated

The full audit trail, recomputed from the verdict data at build time through the same code that produced the leaderboard: verdict × quality × story weight per cell, cells sum to dimension scores, dimensions blend into the PA Score. Every number on the product page is reproducible from this page alone; for why the formula looks like this, see the methodology.

verdict factors: full ×1.0 · partial ×0.6 · disputed ×0.3 · none ×0.0 · n/a excluded from both sides · cell points = weight × quality × factor · cell max = weight × 10

PA Score26/100

Agent-ready 27.9 × 0.30 = 8.37

API quality 0.0 × 0.20 = 0.00

Openness 54.4 × 0.20 = 10.88

Built-in AI 30.7 × 0.15 = 4.60

Automation 15.0 × 0.15 = 2.25

(8.37 + 0.00 + 10.88 + 4.60 + 2.25) ÷ (0.30 + 0.20 + 0.20 + 0.15 + 0.15) = 26.11 ÷ 1.00 = 26.1

Scores are stored to 1 decimal; the product page’s pills round to whole numbers for display. Each dimension below shows the stories, verdicts, and cited evidence behind its number.

Agent-ready27.9/100×0.30 of the PA blend

Outside-in: can YOUR agent reach and drive this product — API, MCP, CLI, headless runs, agent docs.

Point an agent at llms.txt or agent-oriented docsweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

  • [probe] https://buzz.xyz/llms.txtPROBE llms.txt: HTTP 404 at https://buzz.xyz/llms.txt

Run the product headlessly / in CI for automationweight 2

2 (weight) × 5 (quality) × 0.6 (partial) = 6.0 of 20 max

  • [claimed-docs] https://raw.githubusercontent.com/block/buzz/main/crates/buzz-cli/README.mdbuzz channels create --name "my-channel" --type stream --visibility open
  • [claimed-docs] https://raw.githubusercontent.com/block/buzz/main/crates/buzz-cli/README.mdbuzz repos protect set --id my-repo --ref refs/heads/main --push admin --no-force-push --no-delete
  • [claimed-docs] https://raw.githubusercontent.com/block/buzz/main/crates/buzz-cli/README.mdbuzz workflows trigger --workflow buzz workflows approve --token
  • [github] https://github.com/block/buzzAgents have their own keys, their own channel memberships, and their own audit trail.
  • [probe] https://github.com/block/buzz/tree/main/crates/buzz-cliofficial CLI documented at https://github.com/block/buzz/tree/main/crates/buzz-cli

Plug MCP servers into this product so it can use their toolsweight 3

3 (weight) × 3 (quality) × 0.6 (partial) = 5.4 of 30 max

  • [probe] https://raw.githubusercontent.com/block/buzz/main/docs/MCP_DRIVEN_HOOKS.mdofficial MCP server documented at https://raw.githubusercontent.com/block/buzz/main/docs/MCP_DRIVEN_HOOKS.md

Connect an agent via an official MCP serverweight 3

3 (weight) × 6 (quality) × 0.6 (partial) = 10.8 of 30 max

  • [probe] https://raw.githubusercontent.com/block/buzz/main/docs/MCP_DRIVEN_HOOKS.mdofficial MCP server documented at https://raw.githubusercontent.com/block/buzz/main/docs/MCP_DRIVEN_HOOKS.md
  • [github] https://github.com/block/buzzAgents have their own keys, their own channel memberships, and their own audit trail.
  • [github] https://github.com/block/buzzopen repos, send patches, review code, run workflows, edit canvases, orchestrate other agents, drop into voice huddles, create channels
  • [community] https://hn.algolia.com/api/v1/items/48995213Commenter says Buzz uses channel-based scoping like humans would, but criticizes that it invented its own auth/permission protocol instead of using an existing one, as if the idea were novel.
  • [community] https://hn.algolia.com/api/v1/items/48995213Critique of Buzz's group permission model: "These kinds of rules never survive real world tests. For example if I create a private group just for myself and auto invite every agent... does that mean no one can now use any of them?"

Use an official CLIweight 2

2 (weight) × 8 (quality) × 1.0 (full) = 16.0 of 20 max

  • [claimed-docs] https://raw.githubusercontent.com/block/buzz/main/crates/buzz-cli/README.mdbuzz channels create --name "my-channel" --type stream --visibility open
  • [claimed-docs] https://raw.githubusercontent.com/block/buzz/main/crates/buzz-cli/README.mdbuzz gifs search # trending GIFs
  • [claimed-docs] https://raw.githubusercontent.com/block/buzz/main/crates/buzz-cli/README.mdbuzz repos protect set --id my-repo --ref refs/heads/main --push admin --no-force-push --no-delete
  • [claimed-docs] https://raw.githubusercontent.com/block/buzz/main/crates/buzz-cli/README.mdbuzz workflows trigger --workflow buzz workflows approve --token
  • [probe] https://github.com/block/buzz/tree/main/crates/buzz-cliofficial CLI documented at https://github.com/block/buzz/tree/main/crates/buzz-cli

Drive the product through a documented public APIweight 3

3 (weight) × 6 (quality) × 0.6 (partial) = 10.8 of 30 max

  • [claimed-docs] https://raw.githubusercontent.com/block/buzz/main/crates/buzz-cli/README.mdbuzz channels create --name "my-channel" --type stream --visibility open
  • [claimed-docs] https://raw.githubusercontent.com/block/buzz/main/crates/buzz-cli/README.mdbuzz repos protect set --id my-repo --ref refs/heads/main --push admin --no-force-push --no-delete
  • [claimed-docs] https://raw.githubusercontent.com/block/buzz/main/crates/buzz-cli/README.mdbuzz workflows trigger --workflow buzz workflows approve --token
  • [github] https://github.com/block/buzzAgents have their own keys, their own channel memberships, and their own audit trail.
  • [probe] https://raw.githubusercontent.com/block/buzz/main/docs/MCP_DRIVEN_HOOKS.mdofficial MCP server documented at https://raw.githubusercontent.com/block/buzz/main/docs/MCP_DRIVEN_HOOKS.md
  • [probe] https://github.com/block/buzz/tree/main/crates/buzz-cliofficial CLI documented at https://github.com/block/buzz/tree/main/crates/buzz-cli
  • [probe] https://buzz.xyz/llms.txtPROBE llms.txt: HTTP 404 at https://buzz.xyz/llms.txt
  • [probe] https://buzz.xyz/openapi.jsonPROBE openapi: all candidate paths 404 (https://buzz.xyz/openapi.json, https://buzz.xyz/swagger.json, https://buzz.xyz/api/openapi.json, https://buzz.xyz/.well-known/openapi.json)

Issue scoped/least-privilege API credentials for an agentweight 2

2 (weight) × 4 (quality) × 0.6 (partial) = 4.8 of 20 max

  • [github] https://github.com/block/buzzAgents have their own keys, their own channel memberships, and their own audit trail.
  • [claimed-docs] https://raw.githubusercontent.com/block/buzz/main/crates/buzz-cli/README.mdbuzz repos protect set --id my-repo --ref refs/heads/main --push admin --no-force-push --no-delete
  • [community] https://hn.algolia.com/api/v1/items/48995213A Slack employee argues multiplayer agents in Buzz risk leaking private data to teammates, requiring complex rulesets about resource access, unlike single-player agents scoped to one user.
  • [community] https://hn.algolia.com/api/v1/items/48995213Commenter says Buzz uses channel-based scoping like humans would, but criticizes that it invented its own auth/permission protocol instead of using an existing one, as if the idea were novel.
  • [community] https://hn.algolia.com/api/v1/items/48995213Critique of Buzz's group permission model: "These kinds of rules never survive real world tests. For example if I create a private group just for myself and auto invite every agent... does that mean no one can now use any of them?"

Build against official SDKsweight 2

2 (weight) × 4 (quality) × 0.6 (partial) = 4.8 of 20 max

  • [probe] https://github.com/block/buzz/tree/main/crates/buzz-cliofficial CLI documented at https://github.com/block/buzz/tree/main/crates/buzz-cli
  • [probe] https://raw.githubusercontent.com/block/buzz/main/docs/MCP_DRIVEN_HOOKS.mdofficial MCP server documented at https://raw.githubusercontent.com/block/buzz/main/docs/MCP_DRIVEN_HOOKS.md
  • [github] https://github.com/block/buzzAgents have their own keys, their own channel memberships, and their own audit trail.
  • [probe] https://buzz.xyz/llms.txtPROBE llms.txt: HTTP 404 at https://buzz.xyz/llms.txt
  • [probe] https://buzz.xyz/openapi.jsonPROBE openapi: all candidate paths 404 (https://buzz.xyz/openapi.json, https://buzz.xyz/swagger.json, https://buzz.xyz/api/openapi.json, https://buzz.xyz/.well-known/openapi.json)

Subscribe to events via webhooksweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Agent-ready = 58.6 ÷ 210 × 100 = 27.9

API quality0.0/100×0.20 of the PA blend

The programmable surface once an agent is there — machine-readable spec, interactive docs, sandbox, versioning discipline.

Explore an interactive API reference with runnable examplesweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

  • [probe] https://buzz.xyz/llms.txtPROBE llms.txt: HTTP 404 at https://buzz.xyz/llms.txt
  • [probe] https://buzz.xyz/openapi.jsonPROBE openapi: all candidate paths 404 (https://buzz.xyz/openapi.json, https://buzz.xyz/swagger.json, https://buzz.xyz/api/openapi.json, https://buzz.xyz/.well-known/openapi.json)
  • [probe] https://github.com/block/buzz/tree/main/crates/buzz-cliofficial CLI documented at https://github.com/block/buzz/tree/main/crates/buzz-cli

Download a machine-readable API spec (OpenAPI or equivalent)weight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

  • [probe] https://buzz.xyz/llms.txtPROBE llms.txt: HTTP 404 at https://buzz.xyz/llms.txt
  • [probe] https://buzz.xyz/openapi.jsonPROBE openapi: all candidate paths 404 (https://buzz.xyz/openapi.json, https://buzz.xyz/swagger.json, https://buzz.xyz/api/openapi.json, https://buzz.xyz/.well-known/openapi.json)

Test against a sandbox environment without touching production dataweight 1

1 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 10 max

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Rely on versioned APIs with a documented deprecation policyweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

  • [probe] https://buzz.xyz/openapi.jsonPROBE openapi: all candidate paths 404 (https://buzz.xyz/openapi.json, https://buzz.xyz/swagger.json, https://buzz.xyz/api/openapi.json, https://buzz.xyz/.well-known/openapi.json)

API quality = 0.0 ÷ 70 × 100 = 0.0

Openness54.4/100×0.20 of the PA blend

Can you leave, inspect, or self-host — data export, open source, portability.

Do everything through the API that I can do in the UIweight 2

2 (weight) × 6 (quality) × 0.6 (partial) = 7.2 of 20 max

  • [github] https://github.com/block/buzzopen repos, send patches, review code, run workflows, edit canvases, orchestrate other agents, drop into voice huddles, create channels
  • [github] https://github.com/block/buzzAgents have their own keys, their own channel memberships, and their own audit trail.
  • [claimed-docs] https://raw.githubusercontent.com/block/buzz/main/crates/buzz-cli/README.mdbuzz channels create --name "my-channel" --type stream --visibility open
  • [claimed-docs] https://raw.githubusercontent.com/block/buzz/main/crates/buzz-cli/README.mdbuzz repos protect set --id my-repo --ref refs/heads/main --push admin --no-force-push --no-delete
  • [claimed-docs] https://raw.githubusercontent.com/block/buzz/main/crates/buzz-cli/README.mdbuzz workflows trigger --workflow buzz workflows approve --token
  • [probe] https://buzz.xyz/openapi.jsonPROBE openapi: all candidate paths 404 (https://buzz.xyz/openapi.json, https://buzz.xyz/swagger.json, https://buzz.xyz/api/openapi.json, https://buzz.xyz/.well-known/openapi.json)
  • [probe] https://github.com/block/buzz/tree/main/crates/buzz-cliofficial CLI documented at https://github.com/block/buzz/tree/main/crates/buzz-cli

Export all of my data in open formats and leaveweight 3

3 (weight) × 4 (quality) × 0.6 (partial) = 7.2 of 30 max

  • [claimed-docs] https://raw.githubusercontent.com/block/buzz/main/VISION.mdNo GitHub. No Discord. No stitching five services together. The project lives in one place, and that place is yours.
  • [claimed-docs] https://raw.githubusercontent.com/block/buzz/main/VISION.mdRun your own relay for one community, or let an operator host thousands on shared infrastructure — same OSS codebase, same URL-is-your-workspace experience either way.
  • [probe] https://github.com/block/buzz/tree/main/crates/buzz-cliofficial CLI documented at https://github.com/block/buzz/tree/main/crates/buzz-cli

Read the product's source under an open licenseweight 2

2 (weight) × 8 (quality) × 1.0 (full) = 16.0 of 20 max

  • [github] https://github.com/block/buzzTurn a feature branch into a room where patches, CI, review, and the merge decision live together — so the channel becomes the record of why the code exists.
  • [github] https://github.com/block/buzzopen repos, send patches, review code, run workflows, edit canvases, orchestrate other agents, drop into voice huddles, create channels
  • [claimed-docs] https://raw.githubusercontent.com/block/buzz/main/VISION.mdNo GitHub. No Discord. No stitching five services together. The project lives in one place, and that place is yours.
  • [community] https://news.ycombinator.com/item?id=48995213"Excited for 'decentralized, self-sovereign, and open source.' Indifferent to 'groupchat for agents'."
  • [probe] https://github.com/block/buzz/tree/main/crates/buzz-cliofficial CLI documented at https://github.com/block/buzz/tree/main/crates/buzz-cli

Self-host the core productweight 3

3 (weight) × 8 (quality) × 1.0 (full) = 24.0 of 30 max

  • [claimed-docs] https://raw.githubusercontent.com/block/buzz/main/VISION.mdNo GitHub. No Discord. No stitching five services together. The project lives in one place, and that place is yours.
  • [claimed-docs] https://raw.githubusercontent.com/block/buzz/main/VISION.mdRun your own relay for one community, or let an operator host thousands on shared infrastructure — same OSS codebase, same URL-is-your-workspace experience either way.
  • [github] https://github.com/block/buzzTurn a feature branch into a room where patches, CI, review, and the merge decision live together — so the channel becomes the record of why the code exists.
  • [probe] https://github.com/block/buzz/tree/main/crates/buzz-cliofficial CLI documented at https://github.com/block/buzz/tree/main/crates/buzz-cli

Openness = 54.4 ÷ 100 × 100 = 54.4

Built-in AI30.7/100×0.15 of the PA blend

Inside-out: how agentic the product itself is for its users — built-in assistants, autonomous features.

Get AI-generated insights and suggestions from my data inside the productweight 2

2 (weight) × 3 (quality) × 0.6 (partial) = 3.6 of 20 max

  • [github] https://github.com/block/buzzAgents search six months of history and post the threads, not vibes.
  • [github] https://github.com/block/buzzopen repos, send patches, review code, run workflows, edit canvases, orchestrate other agents, drop into voice huddles, create channels
  • [github] https://github.com/block/buzzSearch the conversation, the patch, the workflow run, and the approval in one place

Set up automations that run autonomously in the backgroundweight 2

2 (weight) × 6 (quality) × 0.6 (partial) = 7.2 of 20 max

  • [github] https://github.com/block/buzzopen repos, send patches, review code, run workflows, edit canvases, orchestrate other agents, drop into voice huddles, create channels
  • [github] https://github.com/block/buzzAgents have their own keys, their own channel memberships, and their own audit trail.
  • [claimed-docs] https://raw.githubusercontent.com/block/buzz/main/crates/buzz-cli/README.mdbuzz workflows trigger --workflow buzz workflows approve --token
  • [probe] https://raw.githubusercontent.com/block/buzz/main/docs/MCP_DRIVEN_HOOKS.mdofficial MCP server documented at https://raw.githubusercontent.com/block/buzz/main/docs/MCP_DRIVEN_HOOKS.md

Delegate tasks to a built-in AI assistant inside the productweight 3

3 (weight) × 6 (quality) × 0.6 (partial) = 10.8 of 30 max

  • [github] https://github.com/block/buzzopen repos, send patches, review code, run workflows, edit canvases, orchestrate other agents, drop into voice huddles, create channels
  • [github] https://github.com/block/buzzAgents have their own keys, their own channel memberships, and their own audit trail.
  • [probe] https://raw.githubusercontent.com/block/buzz/main/docs/MCP_DRIVEN_HOOKS.mdofficial MCP server documented at https://raw.githubusercontent.com/block/buzz/main/docs/MCP_DRIVEN_HOOKS.md
  • [github] https://github.com/block/buzzAgents search six months of history and post the threads, not vibes.

Operate the product with natural-language commandsweight 2

2 (weight) × 5 (quality) × 0.6 (partial) = 6.0 of 20 max

  • [github] https://github.com/block/buzzopen repos, send patches, review code, run workflows, edit canvases, orchestrate other agents, drop into voice huddles, create channels
  • [claimed-docs] https://raw.githubusercontent.com/block/buzz/main/crates/buzz-cli/README.mdbuzz channels create --name "my-channel" --type stream --visibility open
  • [claimed-docs] https://raw.githubusercontent.com/block/buzz/main/crates/buzz-cli/README.mdbuzz repos protect set --id my-repo --ref refs/heads/main --push admin --no-force-push --no-delete
  • [claimed-docs] https://raw.githubusercontent.com/block/buzz/main/crates/buzz-cli/README.mdbuzz workflows trigger --workflow buzz workflows approve --token
  • [probe] https://raw.githubusercontent.com/block/buzz/main/docs/MCP_DRIVEN_HOOKS.mdofficial MCP server documented at https://raw.githubusercontent.com/block/buzz/main/docs/MCP_DRIVEN_HOOKS.md
  • [probe] https://github.com/block/buzz/tree/main/crates/buzz-cliofficial CLI documented at https://github.com/block/buzz/tree/main/crates/buzz-cli

Built-in AI = 27.6 ÷ 90 × 100 = 30.7

Automation15.0/100×0.15 of the PA blend

Depth of automation primitives — rules, scheduling, bulk operations, webhooks.

Perform bulk operations across many items at onceweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

  • [claimed-docs] https://raw.githubusercontent.com/block/buzz/main/crates/buzz-cli/README.mdbuzz channels create --name "my-channel" --type stream --visibility open
  • [claimed-docs] https://raw.githubusercontent.com/block/buzz/main/crates/buzz-cli/README.mdbuzz repos protect set --id my-repo --ref refs/heads/main --push admin --no-force-push --no-delete
  • [claimed-docs] https://raw.githubusercontent.com/block/buzz/main/crates/buzz-cli/README.mdbuzz workflows trigger --workflow buzz workflows approve --token

Define rules that trigger actions automatically on eventsweight 3

3 (weight) × 5 (quality) × 0.6 (partial) = 9.0 of 30 max

  • [claimed-docs] https://raw.githubusercontent.com/block/buzz/main/crates/buzz-cli/README.mdbuzz workflows trigger --workflow buzz workflows approve --token
  • [probe] https://raw.githubusercontent.com/block/buzz/main/docs/MCP_DRIVEN_HOOKS.mdofficial MCP server documented at https://raw.githubusercontent.com/block/buzz/main/docs/MCP_DRIVEN_HOOKS.md
  • [probe] https://github.com/block/buzz/tree/main/crates/buzz-cliofficial CLI documented at https://github.com/block/buzz/tree/main/crates/buzz-cli

Schedule recurring jobs or workflowsweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Version, review, and roll back my automationsweight 1

1 (weight) × 5 (quality) × 0.6 (partial) = 3.0 of 10 max

  • [github] https://github.com/block/buzzTurn a feature branch into a room where patches, CI, review, and the merge decision live together — so the channel becomes the record of why the code exists.
  • [github] https://github.com/block/buzzSearch the conversation, the patch, the workflow run, and the approval in one place
  • [claimed-docs] https://raw.githubusercontent.com/block/buzz/main/crates/buzz-cli/README.mdbuzz repos protect set --id my-repo --ref refs/heads/main --push admin --no-force-push --no-delete
  • [claimed-docs] https://raw.githubusercontent.com/block/buzz/main/crates/buzz-cli/README.mdbuzz workflows trigger --workflow buzz workflows approve --token

Automation = 12.0 ÷ 80 × 100 = 15.0