Agnost AI
Product analytics for AI agents to track intents, drop-offs, and retention.
Website: https://agnost.ai/
Cover Block
| Field | Value |
|---|---|
| Name | Agnost AI |
| Tagline | Product analytics for AI agents to track intents, drop-offs, and retention |
| Headquarters | San Francisco, United States |
| Founded | 2024 |
| Stage | Pre-Seed |
| Business Model | SaaS |
| Industry | Developer tools / AI observability |
| Technology Type | AI / Machine Learning |
| Geography | North America |
| Growth Profile | Venture Scale |
| Founding Team | Co-Founders (2) |
| Funding Label | Pre-Seed |
Links
- Website: https://agnost.ai/
- Documentation: https://docs.agnost.ai
- Blog: https://agnost.ai/blog/
- LinkedIn (founder, Shubham Palriwala): https://www.linkedin.com/in/shubhampalriwala/
- LinkedIn (founder, Shubham Patel): https://www.linkedin.com/in/shubham-patel-80203a219/
- X / Twitter: https://x.com/agnostai
- npm package: https://www.npmjs.com/package/agnost
- PitchBook profile: https://pitchbook.com/profiles/company/1258139-80
Summary and Signal
Agnost AI is a San Francisco pre-seed company building product analytics specifically for AI agents and Model Context Protocol (MCP) servers [Agnost AI]. The company was founded in 2024 by Shubham Palriwala (Cofounder and CEO) and Shubham Patel, with Palriwala bringing roughly five years of backend engineering experience across Cisco, Formbricks, Onboarding.club and Google Season of Docs [RocketReach; GetProg.ai]. The product surfaces conversation-level metrics, intent conversion, drop-off points, satisfaction signals and a proprietary Agent Experience Score, distributed via Python and JavaScript SDKs [Agnost AI Docs; Agnost AI Blog]. Backers disclosed to date include Entrepreneurs First and Transpose Platform [PitchBook]. The business model is SaaS aimed at developer teams building agents, MCP servers and plugins [Agnost AI Blog].
Data Accuracy: YELLOW -- Founder identities and product scope confirmed by company sources, LinkedIn and RocketReach; funding details remain undisclosed.
Taxonomy Snapshot
| Axis | Value |
|---|---|
| Stage | Pre-Seed |
| Business Model | SaaS |
| Industry / Vertical | Developer tools, AI observability |
| Technology Type | AI / Machine Learning, analytics SDKs |
| Geography | North America (San Francisco) |
| Growth Profile | Venture Scale |
| Founding Team | Two technical co-founders |
| Funding | Pre-Seed, amount undisclosed |
Company Overview
Agnost AI was incorporated in 2024 and operates out of San Francisco, with its X account joined in October 2024 [X, October 2024]. The founding thesis is that conventional product analytics tools were designed for click-and-pageview funnels and do not capture the unit of value in agent products, which is the conversation and the intent it resolves [Agnost AI Blog]. The company positions itself as the analytics layer for AI-native products, with native instrumentation for MCP servers, plugins and tool calls.
Shubham Palriwala serves as Cofounder and CEO [LinkedIn; YouTube]. Shubham Patel, who previously studied at the University of Texas at Dallas, is the second co-founder [LinkedIn]. Investors disclosed publicly are Entrepreneurs First and Transpose Platform.
Key milestones include company formation in 2024, publication of the Python SDK and MCP-focused npm package (version 0.1.10) [npm], a cadence of technical blog posts on MCP analytics, and podcast appearances by Palriwala [YouTube].
Data Accuracy: YELLOW -- Founding year, location and founders cross-confirmed; legal entity, exact incorporation date and milestone dates beyond 2024 are not publicly available.
The Product and the Stack
The product is an analytics platform purpose-built for AI agents and MCP servers. The core surface is a Conversation SDK that lets developers track AI interactions, monitor performance, and analyze conversations in Python applications [Agnost AI Docs]. A JavaScript/Node distribution is published as the agnost npm package, currently at version 0.1.10 with nine dependent projects [npm]. The instrumentation captures conversation-level events, tool and plugin invocations, MCP task lifecycles, and satisfaction signals [Agnost AI Blog].
Derived constructs include the Agent Experience Score, with benchmarks for customer support agents in the 72-80 range [Agnost AI Blog]. Other named metrics include an Intent Resolution Rate proxy, a Frustration Index, Health Scoring and per-customer cost attribution for Apify Actors [Agnost AI Docs; Agnost AI Blog]. The blog discusses long-running MCP task patterns under SEP-1686 [Agnost AI Blog].
Data Accuracy: GREEN -- Product surface, SDK availability and named metrics confirmed by Agnost AI's documentation, blog and the npm registry.
Market Research and Opportunity
Agent analytics is emerging as a distinct subcategory inside the broader AI observability and developer tools market. Product analytics broadly is an established multi-billion-dollar software category, and AI/LLM observability has materialized in the past 24 months as a parallel category aimed at model and prompt monitoring. Agnost positions itself at the intersection: conversation-and-intent analytics for shipped agent products.
Demand drivers include the Model Context Protocol creating a new server type whose operators need usage metrics [Agnost AI Blog]. The company argues that AI products fail on dimensions traditional analytics cannot see, such as resolution without satisfaction [Agnost AI Blog]. Customer support is cited as the most mature agent vertical, with benchmarks of 72-80 on the Agent Experience Score [Agnost AI Blog].
| Metric | Value |
|---|---|
| Agent Experience Score range, customer support agents | 72-80 |
Public dependents on agnost npm package |
9 |
Current agnost npm version |
0.1.10 |
Data Accuracy: YELLOW -- Category signals and product benchmarks sourced from Agnost AI's blog and the npm registry; no independent third-party market sizing for agent analytics specifically was located.
The Competitive Field
Agnost is positioned as a focused agent-and-MCP analytics specialist competing against LLM observability platforms and broader product analytics incumbents. The segment map includes LLM observability platforms (LangSmith, Arize AI, Helicone, Braintrust, Langfuse), incumbent product analytics (PostHog, Amplitude, Mixpanel, Heap), and platform-native telemetry (OpenAI, Anthropic, AWS Bedrock).
Agnost's edge includes native MCP support and an opinionated metric layer (Agent Experience Score, Frustration Index). Exposure exists in distribution and brand, as incumbents possess larger install bases and enterprise observability budgets.
Opportunity
The headline opportunity
Agnost could become the default analytics layer for AI agents and MCP servers. The category is new, the company has shipped working SDKs in Python and JavaScript, and it has staked out an opinionated metric vocabulary [Agnost AI Blog; npm].
Growth scenarios
| Scenario | What happens | Catalyst |
|---|---|---|
| MCP standard rides | Agnost becomes the reference analytics SDK in MCP server tutorials | Inclusion in MCP server templates |
| Support-agent vertical wedge | Agnost becomes the benchmarking standard for customer support agents | Flagship customer publishes results using benchmarks |
| Embedded analytics for agent platforms | Agnost is bundled as the analytics layer inside vertical agent platforms | Partnership or OEM deal |
What compounding looks like
The flywheel involves developer adoption of the SDK creating an event corpus, which enables benchmarking that becomes a content and sales engine. There are nine public dependents on the agnost npm package and a published benchmark range for support agents [npm; Agnost AI Blog].
Data Accuracy: YELLOW -- Scenarios grounded in cited product capabilities and category signals from Agnost AI's own materials and the npm registry.
Sources
- [Agnost AI] Agnost: Product Analytics for AI Agents | https://agnost.ai/
- [Agnost AI Docs] Getting Started - Agnost AI | https://docs.agnost.ai
- [Agnost AI Blog] Blog index | https://agnost.ai/blog/
- [Agnost AI Blog] Long Running Tasks in MCP: The Call-Now, Fetch-Later Pattern | https://agnost.ai/blog/long-running-tasks-mcp/
- [Agnost AI Blog] How to Build Your Own Claude Code Plugin | https://agnost.ai/blog/claude-code-plugins-guide/
- [Agnost AI Blog] Resolution Without Satisfaction: Agent Experience | https://agnost.ai/blog/resolution-without-satisfaction-agent-experience/
- [Agnost AI Blog] Agent Experience Score | https://agnost.ai/blog/agent-experience-score/
- [Agnost AI Blog] How to Improve Your MCP Server | https://agnost.ai/blog/mcp-analytics-guide/
- [Agnost AI Blog] How to Get More Usage on Your MCP Server | https://agnost.ai/blog/increase-mcp-server-usage/
- [Agnost AI Blog] The 6 Metrics Every AI-Native Product Should Track | https://agnost.ai/blog/6-metrics-every-ai-native-product-should-track/
- [Agnost AI Docs] Apify Actors integration | https://docs.agnost.ai/apify
- [Agnost AI Docs] Roadmap | https://docs.agnost.ai/roadmap
- [npm] agnost package page | https://www.npmjs.com/package/agnost
- [X, October 2024] Agnost AI (@agnostai) | https://x.com/agnostai
- [LinkedIn] Shubham Palriwala profile | https://www.linkedin.com/in/shubhampalriwala/
- [LinkedIn] Shubham Patel profile | https://www.linkedin.com/in/shubham-patel-80203a219/
- [GetProg.ai] Shubham Palriwala, Co-Founder at Agnost AI | https://www.getprog.ai/profile/55556994
- [RocketReach] Shubham Palriwala, Agnost AI Co-Founder | https://rocketreach.co/shubham-palriwala-email_628647369
- [PitchBook] Agnost AI company profile | https://pitchbook.com/profiles/company/1258139-80
- [AIToolBook] Agnost Review | https://aitoolbook.ai/ai/agnost
- [YouTube] The Hidden Metrics Behind Successful MCP Servers, with Shubham Palriwala | https://www.youtube.com/watch?v=9BXrlbFlAQs
- [YouTube] MCP Analytics Q&A with Shinzo Labs and Agnost AI | https://www.youtube.com/watch?v=JVpbUbS73U4
- [Weekday] Shubham Palriwala profile | https://www.weekday.works/people/shubham-palriwala-shubhampalriwala
Articles about Agnost AI
- Agnost AI Wants Every MCP Server to Run on the Same Stopwatch — The San Francisco pre-seed, backed by Entrepreneurs First, is selling conversation-level analytics to teams shipping AI agents into production.