Prompt Assay
promptassay.ai
- Free plan
- Web
- API
What Prompt Assay is
Prompt Assay is a workbench for authoring, refining, versioning, testing, and shipping LLM prompts and Agent Skills. Its critique feature rates clarity, completeness, structure, technique use, robustness, and efficiency, with written explanations. An in-editor AI pair can brainstorm, critique, improve, rewrite, compare, and convert content. Users can connect their own Anthropic, OpenAI, or Google models and run one prompt across two to five models in parallel, comparing outputs, latency, token use, and cost; optional LLM-as-Judge scoring is available. For Agent Skills, the workbench supports multi-file bundles, critique, and Behavioral Evals across Claude, GPT, and Gemini. Imports accept Markdown, Anthropic JSON, OpenAI JSON, or raw text, and its bundle retains versions, tags, fragments, and metadata. The free plan includes 250 calls per month for one seat, with seven initial platform-funded calls; BYOK is needed for continued use. Solo costs $49 a month and includes API and SDK access. The public REST API and TypeScript SDK require Solo or higher.
Who it suits
Prompt Assay suits prompt engineers, teams managing shared prompt libraries, researchers comparing models, and developers retrieving prompts through an API or SDK. The free tier may suit a single user evaluating the workbench, with BYOK needed for ongoing use.
Good to know, and what to watch
- Critique includes written reasons across six prompt qualities.
- Compare outputs from two to five models in parallel.
- Supports multi-file Agent Skill bundles and Behavioral Evals.
- Imports several prompt formats and preserves bundle metadata.
- Free plan includes 250 calls per month.
- Free plan is limited to one seat.
- Ongoing free-tier use requires BYOK.
- Public REST API and TypeScript SDK require Solo or higher.
- Prompt Assay says it does not currently hold SOC 2 or ISO 27001 attestations.
Plans
Every plan and priceEnterprise
Free
Solo
Team
Free plan
The verdict
Prompt Assay combines prompt editing, critique, model comparison, and Agent Skill evaluation in one workbench. Check the call and seat limits, BYOK requirement, and tier needed for API access before choosing a plan.
What the maker publishes
- Agent Skills
- Users can author multi-file Agent Skill bundles, critique them, and run Behavioral Evals across Claude, GPT, and Gemini. source
- AI actions
- The in-editor AI pair offers brainstorm, critique, improve, rewrite, compare, and convert actions. source
- API
- The public REST API and TypeScript SDK require Solo tier or higher; API requests are authenticated with an API key. source
- Critique
- Its prompt critique scores clarity, completeness, structure, technique usage, robustness, and efficiency, with written reasons. source
- Data retention
- Provider responses are generally not retained server-side, with evaluation test outputs and Skills Behavioral Eval results as stated exceptions. source
- Free tier limit
- Free includes 250 calls per month and one seat; seven initial platform-funded calls are available before BYOK is needed for ongoing use. source
- Imports and exports
- Prompt imports support Markdown, Anthropic JSON, OpenAI JSON, and raw text; the Prompt Assay bundle preserves versions, tags, fragments, and metadata. source
- Intended users
- The maker describes the product for prompt engineers, teams sharing prompt libraries, researchers evaluating models, and developers retrieving prompts through an API or SDK. source
- Key handling
- Provider API keys are encrypted at rest, never appear in logs, and are used only for LLM calls the user triggers. source
- Maker
- Jon Lasley founded Prompt Assay; the About page describes his enterprise technology and applied AI experience but does not state a founding year or headquarters. source
- Model comparison
- Users can run one prompt across 2–5 BYOK models in parallel and compare outputs, latency, tokens, and cost, with optional LLM-as-Judge scoring. source
- Model providers
- The workbench supports BYOK connections to Anthropic, OpenAI, and Google models. source
- Product
- Prompt Assay is a workbench for authoring, refining, versioning, testing, and shipping LLM prompts and Agent Skills. source
- Training and certifications
- Prompt Assay says it does not train on customer content and does not currently hold SOC 2 or ISO 27001 attestations. source
Checked against the maker's pages on 7 Oct 2026.