70% of your AI tokens
are wasted on bad prompts.

We catch them before the agent runs. promptly review scores every prompt against your team’s standards. promptly optimize finds the workflow patterns wasting the most. Both ship dollar-quantified fixes you apply in one click — for prompts, skills, hooks, and model selection.

$ npm i -g @getpromptly/cli

Migrating from Helicone? It’s in maintenance mode after the Mintlify acquisition — Promptly is built for the developer-side of AI spend (sessions, tickets, dollar cost), not raw API traces.

Terminal
| PR MPTLY |
My Sessions Acme Team
0
Sessions
$0
Est. Cost
0m
Total Time
Monthly Budget $892 / $1,250
Team members
AK
SJ
MR
+2
FEAT-142 AKAlex opus-4 $3.42
BUG-89 SJSarah gpt-4o $1.87
FEAT-143 MRMike sonnet $0.94

What it does

Review every prompt

  • LLM judge scores each prompt on intent clarity, context, scope, cost-efficiency, and safety
  • Catches underspecified intent that wastes 2–3 turns of negotiation
  • Suggests a rewrite that would have hit the goal in one shot

Find the patterns wasting the most

  • Detects repetitive workflows that should be skills or hooks
  • Spots Opus-on-trivial-task model mismatches
  • Quantifies the savings in dollars, per pattern

See where the spend actually went

  • Dollar cost per session, per developer, per ticket
  • Sessions tied to JIRA / Linear issues
  • Monthly budgets with threshold alerts

Prompt Review

promptly review — verdict on the prompt, before the agent runs

Workflow Optimizer

promptly optimize — finds the patterns wasting the most

Multi-tool

Claude Code, Codex CLI, Gemini CLI, VS Code, Cursor, Windsurf

Local-first

Your prompts, code, and file paths never leave your machine

How it works

promptly init # auto-detects your AI tools
promptly start TICKET-1 # starts capturing the session
# ... code with any AI tool ...
promptly finish # calculates cost, saves to dashboard

✓ Session saved: 24,521 tokens · $3.42 · 47m

Security & Privacy

Data isolation

Your sessions are yours. Team sessions are only visible to team members with strict access controls.

Role-based access

Owner, Admin, Member roles. Control who can invite, manage, or view team data.

Your code stays private

Conversation data is isolated per-user and per-team. No cross-tenant data access.

Local-first option

Keep everything on your machine. SQLite database, no cloud required. Full offline support.

Pricing

Free

$0
  • promptly review (bring your own Anthropic key)
  • promptly optimize (no API key needed)
  • Unlimited sessions
  • Cost estimates (250+ models)
  • Local dashboard
  • Local-first — nothing leaves your machine