profile: reframe org README as 'Spend controls for Voice AI' - #21
Merged
Conversation
- New hero + 'The problem' (token router ~40%, BYOK dashboards show $0, the join + enforcement; validated 38ms p50 / ~180ms p99 keyless-prod latency). - 'Three ways in': inside your platform (Vapi/Retell/Bland hooks), BYOK, keyless. - Remove the Roadmap (credit lines / trust record), the wallet/stablecoin/x402 framing, 'budget not a balance', and the budget-advisory bullet (docs-only now). - Keep verbatim: the 3-curl one-turn quickstart, MCP block, BYOK base_url snippet, marketplace + framework tables. - Add merged voice recipes (vapi-custom-llm, retell-custom-llm, vapi-voice-metered). Accuracy corrections vs the source draft: kept '300 API credits' (not 200); dropped the non-existent Bland custom-LLM recipe (Bland is reconcile-only) and the non-existent coverage calculator; linked real gitbook pages.
📝 WalkthroughWalkthroughThe profile README now presents Floe as a voice-AI spend-control platform. It documents enforcement behavior, a unified voice-turn quickstart, three integration paths, keyless usage, response-cost reporting, and updated repository links. ChangesVoice-AI spend controls
Estimated code review effort: 1 (Trivial) | ~5 minutes Possibly related PRs
Poem
🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
✨ Finishing Touches🧪 Generate unit tests (beta)
Comment |
Contributor
There was a problem hiding this comment.
Pull request overview
This PR reframes the organization profile README around the new positioning “Spend controls for Voice AI”, restructuring the narrative to emphasize multi-vendor cost joining and pre-spend enforcement for voice stacks.
Changes:
- Replaces the opening positioning and “Why Floe” section with a new “The problem” framing and updated quickstart heading.
- Adds a “Three ways in” section (platform hooks, BYOK, keyless) and consolidates voice recipes links.
- Removes roadmap/credit framing and updates repo descriptions to match the new focus.
💡 Add a code-review agent skill or configure MCP servers for context-aware, tailored reviews. Learn more in the docs.
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@profile/README.md`:
- Line 5: Update the README headline and the referenced coverage metrics to use
one consistent cost denominator and accurately describe enforcement modes.
Revise the line-5 claim to qualify pre-call, media-hook, and Reconcile Mode
coverage across Vapi, Retell, Bland, and BYOK; align the LLM percentage in the
line-20 metric with the custom-LLM coverage described near line 66, and clarify
that reconciliation blocks subsequent calls rather than enforcing the full bill
before payment.
🪄 Autofix
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: ASSERTIVE
Plan: Pro
Run ID: 07934437-444d-4534-bf5e-611848c2aa9d
📒 Files selected for processing (1)
profile/README.md
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Reframes the org profile around Spend controls for Voice AI per the new positioning, validated against the shipped product.
Kept verbatim: the 3-curl one-turn quickstart (shared
X-Floe-Task-Id), the MCP block, the BYOKbase_urlsnippet, and the Marketplace + Framework tables.Removed: the Roadmap (credit lines / trust record), the wallet/stablecoin/x402 framing, "budget not a balance", and the budget-advisory bullet (docs-only now).
Added: "The problem" (token router ~40% vs 100%, BYOK $0 dashboards), "Three ways in" (platform hooks / BYOK / keyless), and the merged voice recipes.
Accuracy corrections vs the source draft (flagging so you can veto):
main—pipecat-livekit-reconcileis still on PR #57, so linking/tree/main/...would 404.Latency 38ms p50 / ~180ms p99 verified against
latency-overhead.md(keyless rail, live prod).Summary by CodeRabbit