Tokenless

Make Your AI Agents Predictable With Graph Engineering - Zachary Blumenfeld, Neo4j

Nov 03, 2026

Interactive discovery

Explore the topic map

Follow the connections between themes, people, and ideas across the Tokenless archive in an interactive topic modeling map.

Open the map Browse posts

Machine Learning

View All

Oct 13, 2026

Judge a Transaction by the Company It Keeps — Somya Rai & MD Sharique, EXL

EXL developed an advanced fraud detection system that augments XGBoost with Graph Neural Network (GNN) embeddings. Traditional tabular models struggle to capture fraud signals residing in transaction neighborhoods. The system's innovative design includes meticulous sampling strategies, disjoint monthly graph construction for leakage control, and a GraphSAGE architecture that aggregates mean, max, and standard deviation of neighbor features to detect subtle fraud patterns. Emphasizing explainability for regulatory compliance and analyst trust, it also features a highly optimized serving architecture achieving 3ms P99 latency, pivoting to edge prediction to reduce cache footprint from 60GB to 2-3GB. This led to a 27-33% relative lift in true positive rates and a projected $65 million incremental fraud capture.

Oct 10, 2026

From 15% to 90% GPU Utilization: Fix the Data Pipeline, Not the Model

Tarun Sunkaraneni from Amazon AGI shows how a multimodal SFT pipeline that spent about 85% of its time waiting on data was brought to roughly 90% GPU utilization. He walks through concurrency with asyncio and Ray actors, prefetching, zero-copy transfer via Ray's object store, and a network-card bottleneck that appears only at scale, and argues that the hardest part of training throughput is often keeping GPUs fed rather than optimizing the model.

Oct 10, 2026

Small Models, Big Results: Training a Finance Agent for Under $500 — Charles Dickens, Snorkel AI

Snorkel AI and UC Berkeley's Sky Computing Lab show that a 4B Qwen3 model, trained with reinforcement learning for under $500 using the rLLM framework, beats its 235B sibling on expert-validated financial question answering built from SEC 10-K filings. The talk covers the FinQA dataset construction and verification, common failure modes of frontier models, transfer to multi-table and general tool-use tasks, and ablations showing that simple data and binary rewards outperform more elaborate setups, since the real bottleneck is disciplined tool use rather than reasoning depth.

Artificial Intelligence

View All

Nov 03, 2026

Make Your AI Agents Predictable With Graph Engineering - Zachary Blumenfeld, Neo4j

A walkthrough of graph engineering, the practice of expressing agent logic as an explicit graph of nodes and routed state. It covers execution, context, and procedural graphs, how skills and decision traces can be compiled into portable graph-shaped skills, and a loan-approval demo showing gains in predictability, governance, and cost.

Nov 03, 2026

Your AI Agents Shouldn't Care Where They Run - Nikhil Harithas, Factory

Factory's Nikhil Harithas explains how Droid, their coding agent, was rebuilt to run on any compute inside a customer's own cloud. The talk covers the Open Compute abstraction, the compute gateway and outbound-only relay design, bring-your-own-key model calls, snapshots and forking for agent swarms, and the operational hard parts of managing compute for long-running agents in regulated enterprises.

Nov 03, 2026

Better Search Took This AI Agent From 36% to 98% Accuracy - Aamir Shakir, Mixedbread

Aamir Shakir of Mixedbread argues that the main limit on agent performance is access to the right data, not model intelligence. He explains why OCR, chunking, single-vector embeddings, and vector databases lose information at each step, and presents a late-interaction, multimodal retrieval approach that embeds document pages visually, with a live demo on Intel earnings reports and a hedge fund case study that raised answer accuracy from 36% to 98%.

Technology

View All

Nov 02, 2026

What iPhone Packaging Reveals About the Robotics Opportunity

Tutor Intelligence CEO Josh Gruenstein explains why robotics is a systems problem spanning AI, hardware, manufacturing, and customers, and how deploying robots into real factories and warehouses, with human tutors as backup, generates the data that makes them more capable. The discussion covers the company's own robot designs, its focus on small and mid-sized businesses, the economics of flexible robotic labor, and the implications for American manufacturing and supply chains.

Oct 29, 2026

Why Founders Are Betting Big on Factories, Mines, and Energy

Erin Price-Wright and Connor Love unpack the AD50 and the rebuilding of America's industrial base, covering how defense demand is financing manufacturing capacity for commercial markets, how AI is reshaping factory economics, how a new generation of founders applies lessons from SpaceX, Tesla, Anduril, and Palantir to mining, energy, and manufacturing, and why private capital is now willing to fund physical infrastructure before government demand is guaranteed.

Oct 28, 2026

Mark Cuban’s Plan to Make Healthcare Affordable

Mark Cuban and Julie Yoo discuss how transparency, direct contracting, and AI could reshape healthcare economics, from Cost Plus Drugs and modular pod manufacturing to personalized medicine, the future of physicians, and advice for founders who want to use AI to learn rather than to stop thinking.

Recent Post

Mar 03, 2026

"Vibe Coding is a Slot Machine" - Jeremy Howard

fast.ai founder Jeremy Howard critiques the 'vibe coding' illusion, arguing that AI-assisted tools create a slot machine-like experience that erodes true software engineering skills. He revisits the origins of ULMFiT, champions interactive programming for building intuition, and reframes AI risk from existential threats to the dangers of power centralization and human enfeeblement.

Mar 03, 2026

Building Planetary-Scale Data Systems with Venice • Felix GV & Olimpiu Pop

Félix GV, architect of LinkedIn's Venice database, explains its unbundled, planetary-scale architecture. He covers their rigorous chaos engineering practices, the trade-offs between consistency and availability in a derived data system, and an experimental integration with DuckDB for advanced analytics and data exploration.

Mar 02, 2026

Beyond Swahili: Designing Inclusive AI for Bantu Languages

Alfred Malingo discusses the unique position of Swahili in AI, arguing that its structural similarities to other Bantu languages make it a far more effective pivot language than English for developing inclusive and accurate models. He deconstructs the failures of typologically mismatched transfer from Indo-European languages and presents a case study, AfriMT-a, to demonstrate how Swahili can serve as a technical bridge for machine translation and representation learning across the Bantu language family.

Mar 02, 2026

Platform Engineering • Ajay Chankramath & Nic Cheneweth • GOTO 2026

Ajay Chankramath and Nic Cheneweth discuss the critical elements of effective platform engineering, emphasizing a product mindset, the foundational role of control planes and API-first design, the common pitfalls of implementing Backstage, and the emerging impact of AI and agents on the platform landscape.

Mar 02, 2026

A2A vs MCP: AI Agent Communication Explained

Discover how A2A (Agent2Agent) and MCP (Model Context Protocol) solve critical challenges in AI agent ecosystems. A2A enables seamless communication and collaboration between diverse AI agents, while MCP standardizes an agent's access to external tools and data, fostering robust and interoperable AI workflows.

Mar 01, 2026

Using Agents in Production: Past Present and Future // Euro Beinat

A deep dive into how Prosus is deploying over 30,000 AI agents to create an 'AI Agentic Workforce'. The talk covers the transition from simple assistants to trusted senior colleagues, the internal tooling developed, and the crucial organizational strategies used to overcome adoption barriers and foster a bottom-up culture of innovation.

← Previous Next →

Stay In The Loop! Subscribe to Our Newsletter.

Get updates straight to your inbox. No spam, just useful content.