CoachLoop
CoachLoop is an AI sales coach that gives every rep personalized coaching after every call.
Core trick
Scores a call transcript against coaching rubrics, then re-scores after a voice-agent practice drill to verify improvement.
Description
CoachLoop is an AI sales coach that gives every rep personalized coaching after every call.
The biggest bottleneck in sales isn't lead generation or CRM software, it's coaching. Sales leaders review calls, identify the behavior costing deals, coach reps, and verify improvement on future calls. The problem is that coaching doesn't scale and as teams grow companies are forced to hire more managers instead of developing reps more effectively.
The cost is significant. Sales leaders cost roughly $250–350k per year, coaching is often the first responsibility they drop, and only about half of sales reps hit quota. Yet teams coached weekly achieve quota attainment rates of 76% versus 47% for teams coached quarterly. For a 40-rep organization carrying a $40M annual quota, that gap can represent roughly $4M in additional revenue.
CoachLoop automates the entire coaching loop. Unlike conversation-intelligence platforms that stop at analytics, CoachLoop closes the loop. It doesn’t just tell managers what happened; it helps reps get better. Every rep receives the equivalent of a dedicated coach after every conversation, enabling organizations to scale coaching, accelerate ramp time, improve quota attainment, and grow revenue without adding management headcount.
The loop coach loop brings to life:
Score → practice → verify improvement.
README excerpt
# CoachLoop AI sales-call coaching loop. Paste a call transcript, get back specific, actionable coaching. > 🛠️ **Built during [Claude Build Day](https://cerebralvalley.ai/e/claude-startups-build-day)** (Anthropic + Cerebral Valley) — San Francisco, 2026-06-13. Open source under MIT. Everything in this repo was built at the event. ## Stack - **Next.js** (App Router) + **TypeScript** - **Anthropic SDK** — Claude **Opus 4.8** (`claude-opus-4-8`) for scoring/coaching/re-score - **ElevenLabs Agents** — realtime voice drill, Claude as the brain - **Tailwind CSS + shadcn/ui** — mobile-first component layer - **Neon Postgres** ## Quickstart (fork-and-run) Fork it, add your own keys, run the whole loop on your own accounts: ```bash npm install cp .env.example .env # fill in ANTHROPIC_API_KEY, ELEVENLABS_API_KEY, ELEVENLABS_AGENT_ID, DATABASE_URL npm run dev # http://localhost:3000 ``` All four env vars are required — see [`.env.example`](.env.example). ## Scripts | Command | Description | | --- | --- | | `npm run dev` | Start the dev server | | `npm run build` | Production build | | `npm run start` | Serve the production build | | `npm run lint` | ESLint | | `npm run typecheck` | `tsc --noEmit` | ## Configuration All declared variables live in [`src/config.ts`](src/config.ts) — hackathon metadata, the target model (`MODEL`), and the `ANTHROPIC_API_KEY` accessor. The only required secret is `ANTHROPIC_API_KEY` (see `.env.example`). ## License [MIT](LICENSE) ©