• Pricing
  • Customers
  • Docs

Open Source

Platform

For Any Agent

FrameworkTS first agentic framework
ObservabilityMetrics, logs, traces
StudioCollaborate, evaluate, iterate
ServerCloud deployment for agents
Memory GatewayAI Gateway with Memory

Get Started

Latest

Books

Workshops

TemplatesAgent projectsMCP CourseAgent base CLI courseVideo CourseVideo course on agents
BlogLatest from Mastra teamResearchResearch and benchmarksChangelogUpdates and improvements
1 • PrinciplesPrinciples of Building AI Agents2 • PatternsPatterns of Building AI Agents
WorkshopsLive sessions with the teamPodcast • Agent HourWeekly livestreams and guests
  • 24.1k
  • LoginSign Up
  • product
    • FrameworkTS first agentic framework
    • ObservabilityMetrics, logs, traces
    • StudioCollaborate, evaluate, iterate
    • ServerCloud deployment for agents
    • Memory GatewayAI Gateway with Memory
  • resources
    Get Started
    • TemplatesAgent projects
    • MCP CourseAgent base CLI course
    • Video CourseVideo course on agents
    Latest
    • BlogLatest from Mastra team
    • ResearchResearch and benchmarks
    • ChangelogUpdates and improvements
    Books
    • 1 • PrinciplesPrinciples of Building AI Agents
    • 2 • PatternsPatterns of Building AI Agents
    Workshops
    • WorkshopsLive sessions with the team
    • Podcast • Agent HourWeekly livestreams and guests
  • more
    • Pricing
    • Customers
    • Docs
    • Contact
  • 24.1k
  • LoginSign Up
Daniel Lew

Daniel Lew

Software Engineer

Daniel Lew is a software engineer at Mastra based in Waterloo. A University of Waterloo graduate with a background in psychology, he previously worked at Netlify and Gatsby.

3 blog posts

Posts by Daniel Lew

Introducing Agent Editor

Edit agent instructions, tools, and display conditions from Studio with draft/publish versioning, or programmatically through the editor API.

Apr 8, 2026
Daniel Lew

Building low-latency guardrails to secure your agents

How we built a suite of out-of-the-box input processors and optimized them from 5000ms to under 500ms per request.

Jul 30, 2025
Daniel Lew

Reducing tool calling error rates from 15% to 3% for OpenAI, Anthropic, and Google Gemini models

We recently built a tool compatibility layer that reduced tool calling error rates from 15% to 3% for 12 OpenAI, Anthropic, and Google Gemini models, across a set of 30 property types and constraints.

May 29, 2025
Daniel Lew
Get weekly updates:
Product
FrameworkStudioServerGateway
Framework
AgentsRAGWorkflowsObservability
Developers
DocsChangelogTemplatesLearn · MCP CourseLearn · Video Course
Resources
BlogResearchBook · PrinciplesBook · PatternsPodcast · Agent Hour
Company
AboutCustomersCareersContact UsNewsletter
Connect
Contact UsGitHubDiscordYouTubeX (Twitter)
SecurityFully operational
Privacyllms.txt