Respan helping more than 100 startups and enterprise teams proactively improve AI agents and prevent hallucinations and failures
Respan Announces $5M in Funding from Gradient, Y Combinator and others
SAN FRANCISCO, March 18, 2026 (GLOBE NEWSWIRE) — Respan, the first proactive AI observability platform that closes the loop from evals to production, announced today that it has raised $5M in funding from Gradient, Y Combinator, Hat-Trick Capital, XIAOXIAO FUND, Antigravity Capital, and Alpen Capital along with prominent angels and AI founders. The company will use the funds for hiring and continuing to scale its AI observability platform.
Respan (previously known as Keywords AI) is also launching a first-of-its-kind automated evaluation agent that lets teams define success with metric-first workflows, continuously evaluates production agent behavior, and turns results into actions teams can ship – prompt updates, regression checks, and automated alerts when quality drifts. Respan is trusted by 100+ AI startups as well as enterprise teams. Today, Respan processes 1B+ logs and 2T+ tokens every month, supporting 6.5M+ end users. The company has experienced more than 8x revenue growth YoY in 2025.
Many teams today use observability and evaluation tools like LangSmith or Braintrust. These tools provide traces, metrics, and AI-based evals that help teams inspect failures and measure quality. But structurally, they stop too early. They answer retrospective questions such as what happened or how this version scored, but they leave the hardest questions unanswered once agents scale.
To manage agents over time, teams need a system that tightly connects Observability, Evaluations, Decisions and Iteration. This system must understand full agent behavior, explicitly handle non-determinism, and evolve alongside the agent itself.
Respan is built to be that system. Unlike competitors, Respan not only offers metrics and scores, but also turns these signals into actions to proactively improve agents.
“Our evals platform gives developers critical metrics and evaluation scores to see how well their AI agents are performing and to view where agents hallucinate so they can take immediate actions to prevent future failures,” said Andy Li, Co-founder of Respan. “We are very excited to officially launch and grateful for the ongoing support of our investors who all bring a deep level of AI experience to the equation.”
“Respan is addressing that gap that exists between evaluations and optimization,” said Denise Teng, Partner at Gradient. “As AI agents scale, it’s not enough to just look at scores; developers need to take action on this insight. Respan built its platform to do this including connections to its own gateway, and we are impressed with how quickly Andy and the team have scaled, working with more than 100 startups and enterprise teams in just a year.”
Proactive Workflow-Level Evaluations for AI Agents
There are three parts to Respan’s platform:
- Observability – log every agent session in production;
- Evaluation – find key metrics use them to evaluate and improve agents;
- Prompt optimization – automatic prompt engineering right in the platform, in production, with live data streams.
At its foundation, Respan provides deep observability: full execution traces across messages, tool calls, routing decisions, memory, environment state, and outcomes. Unlike traditional observability tools, Respan does not stop at visibility.
On top of this data, Respan runs proactive, workflow-level evaluations embedded directly into how agents are built, tested, and shipped. Evaluations are triggered automatically when something meaningful changes – prompts, workflows, routing logic, models, or production behavior.
Because it has access to full traces, historical baselines, production distributions, and evaluation context, Respan’s agents can analyze failures across trials, localize root causes to specific decisions, recommend what evals to add next, decide when capability evals should become regressions, and intelligently sample production traffic for review.
One of the many companies using Respan is Apten, which provides omni-channel AI agents for lead conversion. “We tried Respan after using another eval platform for over a year,” said Roshan Kumaraswamy, co-founder & CTO of Apten. “We found Respan to be much faster and more intuitive, and their support is amazing – they listen to feedback and always respond instantly. I used to spend at least an hour trying to reproduce and fix every agent bug. Now, whenever we have a problem with an agent, the first place I check is Respan and I can instantly see what’s going on. Any company that’s building on LLMs and doesn’t want to be in the dark on what agents are doing needs Respan.”
About Respan
Respan is the first proactive AI observability platform that closes the loop from evals to production. It automatically evaluates production behavior to turn results into concrete changes teams can ship. Unlike competitors, Respan not only offers metrics and scores, but also turns these signals into actions to proactively improve agents. Hundreds of startups and enterprise teams rely on Respan to turn AI agent observability and evaluation into actions. Headquartered in San Francisco, Respan is backed by leading investors including Gradient, Y Combinator, Hat-Trick Capital, XIAOXIAO FUND, Antigravity Capital, and Alpen along with prominent angels and AI founders.
Kerry Metzdorf
Big Swing Communications
978-463-2575
kerry@big-swing.com
A photo accompanying this announcement is available at https://www.globenewswire.com/NewsRoom/AttachmentNg/bf13509b-64d4-4462-8c49-af51a90411ac
