The Agile Monkeys Labs

Research on Information Retrieval, AI, Machine Learning, and more!

The State of AI Document Parsing: Practical Findings for Production Teams

ai
document parsing
ocr
benchmarking
production

64 controlled runs comparing GPT-5.1, Claude Sonnet 4.5, AWS Textract, Azure Document Intelligence, and Google DocAI across passports, certificates, and tax forms.

Dec 11, 2025

Testing in the Era of AI

ai
testing
e2e
automation
stagehand

From ChatGPT experiments to production-ready E2E testing: how Stagehand, Browserbase, and Gemini 2.5 Flash enabled a 70% reduction in test execution time.

Nov 24, 2025

AI Evals Aren’t a Tool. They’re a Mindset.

ai evals
data pipelines
product analytics

Evals is not a UI, or a dashboard, or a platform — it’s about data. Understanding what evaluating really means and building a culture of continuous evaluation.

Nov 17, 2025

AGI Is Still a Decade Away, And the Real Work Starts Now

AGI
AI agents
model optimization
information retrieval
AI strategy

Highlights and reflections from The Agile Monkeys team discussion on Andrej Karpathy’s interview with Dwarkesh Patel — exploring cognitive cores, autonomous agents, and the practical path to AI integration.

Nov 13, 2025

Safely Migrating Production from GPT-4o to GPT-4.1: An Evaluation-Driven Approach

LLM
Evaluation
GPT-4
Production

How we migrated models in production while minimizing risks through a comprehensive multi-level evaluation system.

Jul 24, 2025

Improving Vector‑Search Recall by Fusing Embeddings from Multiple Modalities

information retrieval
e-commerce
research
embeddings

Fusing multiple modalities embeddings have demonstrated consistent improvements (14% over just image embeddings) in fashion e-commerce retrieval.

Jul 24, 2025

Don’t Shrink Your Prompt, Specialize Your Models

fine-tuning
ecommerce
feature-extraction

Putting the mega‑prompt vs micro‑models hypothesis to the test — can specialization really beat size?

Jul 24, 2025

Is Apache NiFi the right tool for your AI data pipelines?

apache nifi
data pipelines
ingestion
information retrieval

Apache NiFi is a powerful visual-coding tool to build data pipelines. We explore its pros and cons and whether it’s the right tool for building your AI data pipelines.

Jul 18, 2025

Don’t Augment Your Generation, Augment Your Retrieval

feature extraction
information retrieval

Feature Augmented Retrieval provides a structured, explicit, and adaptive framework that significantly enhances retrieval accuracy and relevance.

Apr 28, 2025
No matching items