profile: voice-first positioning + voice quickstart - #14
Conversation
- Subtitle: 'One key for your voice agent's entire bill — LLM, voice, telephony, data' (generic line kept as the second sentence). - Add the 40% vs 100% framing (token router meters LLM only; Floe meters the whole call). - Name budget-aware routing as a feature with the concrete result.budgetAdvisory detail (was buried inside 'context-aware budgets'). - Quickstart is now a voice turn (STT -> LLM -> TTS on one key, one task budget), not an AgentKit + Exa web-search example. - Voice marketplace row: Deepgram · ElevenLabs · Venice AI · Twilio (soon); fix the malformed Compute row. - Repos: add floe-guard (public) and eve-floe (reference voice agent); cookbook link already canonical. - Drop ElizaOS from the frameworks table (consistent with the docs).
|
Caution Review failedThe pull request is closed. ℹ️ Recent review info⚙️ Run configurationConfiguration used: Organization UI Review profile: ASSERTIVE Plan: Pro Run ID: 📒 Files selected for processing (1)
📝 WalkthroughWalkthroughThe profile README now positions Floe as a voice-agent billing layer, replaces the previous quickstart examples with curl-based voice-turn requests, and updates marketplace, framework, and repository listings. ChangesProfile README refresh
Estimated code review effort: 1 (Trivial) | ~5 minutes Possibly related PRs
Poem
✨ Finishing Touches🧪 Generate unit tests (beta)
Comment |
There was a problem hiding this comment.
Pull request overview
Updates the organization profile README to position Floe around voice-agent spend (STT/LLM/TTS/telephony) and provide a voice-centric quickstart experience.
Changes:
- Rewrites the headline/subtitle and “Why Floe” framing to emphasize voice-first metering (100% of call spend vs token router ~40%).
- Replaces the previous AgentKit/Exa quickstart with a “one voice turn” (STT → LLM → TTS) curl-based walkthrough using a shared task id.
- Refreshes marketplace/framework/repos tables (voice vendors, removes ElizaOS row, reconciles/extends repo links).
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
|
|
||
| **The spend layer for AI agents.** One endpoint to pay across any LLM or voice vendor API services, | ||
| with programmable, context-aware budgets. Walletless. | ||
| **One key for your voice agent's entire bill — LLM, voice, telephony, data.** One endpoint to pay across any LLM or voice vendor API services, with programmable, context-aware budgets. Walletless. |
Optimizes the org profile README for voice AI builders.
result.budgetAdvisorydetail (was buried in "context-aware budgets").floe-guard(public) andeve-floe(reference voice agent).floe-examplesredirects tofloe-cookbook— both resolve.Backend API untouched.
Summary by CodeRabbit