- Home
- Prompt Management Software
- Prompt Assay
Prompt Assay
What it is
Prompt Assay is a workbench for authoring, refining, versioning, testing, and shipping prompts and Agent Skills. Its critique tool scores clarity, completeness, structure, technique usage, robustness, and efficiency, and provides written reasons. 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 a prompt across two to five models in parallel, comparing outputs, latency, token use, and cost, with optional LLM-as-Judge scoring.
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; its bundle preserves versions, tags, fragments, and metadata. The free plan includes one seat and 250 calls per month, with seven initial platform-funded calls before BYOK is needed for ongoing use. Solo is $49 a month, while Team is $99 per seat per month with a three-seat minimum. The public REST API and TypeScript SDK require Solo or higher.
For and against
For
- Critiques prompts across six stated dimensions.
- Compares outputs from two to five models.
- Supports multi-file Agent Skill bundles and evaluations.
- Imports several prompt formats.
- Provider API keys are encrypted at rest.
Against
- Free plan is limited to one seat.
- Free plan includes 250 calls per month.
- Ongoing free-tier use requires BYOK.
- API and SDK require Solo or higher.
The verdict
Prompt Assay brings prompt and Agent Skill authoring, evaluation, and versioning into one workbench. Check the free-tier call limit and paid-tier requirements for API access before choosing a plan.
Who it suits
Prompt Assay is suited to prompt engineers, teams sharing prompt libraries, researchers comparing models, and developers retrieving prompts through an API or SDK.
Plans and prices
Solo
Unlimited AI calls on your keys · full prompt and Skill version history · public REST API and TypeScript SDK · single seat
Read 7 Oct 2026 · promptassay.ai
Team
3 to 15 seats · shared org library and evaluation suites · owner, admin, and member roles
Read 7 Oct 2026 · promptassay.ai
Enterprise
Unlimited seats · SAML SSO · custom tier controls · data processing agreement
Read 7 Oct 2026 · promptassay.ai
Free
7 platform-funded calls to start · 250 AI calls a month · single seat · 7-day version view
Read 7 Oct 2026 · promptassay.ai
On the record
- Agent Skills
- Users can author multi-file Agent Skill bundles, critique them, and run Behavioral Evals across Claude, GPT, and Gemini.promptassay.ai · read 7 Oct 2026
- AI actions
- The in-editor AI pair offers brainstorm, critique, improve, rewrite, compare, and convert actions.promptassay.ai · read 7 Oct 2026
- API
- The public REST API and TypeScript SDK require Solo tier or higher; API requests are authenticated with an API key.promptassay.ai · read 7 Oct 2026
- Critique
- Its prompt critique scores clarity, completeness, structure, technique usage, robustness, and efficiency, with written reasons.promptassay.ai · read 7 Oct 2026
- Data retention
- Provider responses are generally not retained server-side, with evaluation test outputs and Skills Behavioral Eval results as stated exceptions.promptassay.ai · read 7 Oct 2026
- 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.promptassay.ai · read 7 Oct 2026
- Imports and exports
- Prompt imports support Markdown, Anthropic JSON, OpenAI JSON, and raw text; the Prompt Assay bundle preserves versions, tags, fragments, and metadata.promptassay.ai · read 7 Oct 2026
- 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.promptassay.ai · read 7 Oct 2026
- Key handling
- Provider API keys are encrypted at rest, never appear in logs, and are used only for LLM calls the user triggers.promptassay.ai · read 7 Oct 2026
- 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.promptassay.ai · read 7 Oct 2026
- 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.promptassay.ai · read 7 Oct 2026
- Model providers
- The workbench supports BYOK connections to Anthropic, OpenAI, and Google models.promptassay.ai · read 7 Oct 2026
- Product
- Prompt Assay is a workbench for authoring, refining, versioning, testing, and shipping LLM prompts and Agent Skills.promptassay.ai · read 7 Oct 2026
- Training and certifications
- Prompt Assay says it does not train on customer content and does not currently hold SOC 2 or ISO 27001 attestations.promptassay.ai · read 7 Oct 2026
