How an Agent Finds Your Docs, and Which Files It Actually Reads
Five file conventions claim to be the standard for AI agents. Here is what each one answers, who really reads it, and the evidence behind both claims.
Retrieval and RAG08
Subject · 21 posts
beginner
Before You Retrieve Anything, Someone Has to Read the PDF
Every retrieval method assumes clean structured text. Getting it out of a PDF is its own problem, and Docling is the 2026 answer worth knowing.
Retrieval and RAG07
Open Knowledge Format, Explained in Plain Words
OKF is a folder of markdown files that tells an AI agent what your data means, who wrote it, who checked it, and when it stops being true.
Retrieval and RAG05
Molecular Docking Without the Jargon: A Key, a Lock, and Both of Them Wobble
What a docking score really is, why the pose matters more than the number, six ways docking lies to you, and where 2026 co-folding models fit.
Machine Learning for Biology06
PageIndex: Retrieval With No Vectors At All
PageIndex indexes a document as its own table of contents and lets a model walk the tree. No embeddings, no chunking, and a route you can show a reader.
Retrieval and RAG04
Peptides 101: The Tiny Molecular Sentences Your Body Writes
What a peptide actually is, why order and side chains carry the information, and why 13 residues is a different modelling problem from 300.
Machine Learning for Biology01
What Is an Agent Harness? The Part Everyone Skips
The five parts of an agent harness: capability surface, meaning, policy, approval and audit. Only two of them are about power.
Agent Harness01
Green Padlock, Zero Headache: Let’s Encrypt SSL for Self-Hosted Dify
Let's Encrypt certificates on a self-hosted Dify behind Nginx: the ACME flow, the nginx reload everyone forgets, and how to test without burning rate limits.
When Your Knowledge Base Should Be a Graph
GraphRAG turns a corpus into entities, communities and LLM-written reports so it can answer whole-corpus questions that top-k retrieval structurally cannot.
Retrieval and RAG02
Retrieval Metrics Demystified: From BM25 Baselines to EM@5 & Answer F1
What BM25, Recall@k, answer-in-context rate and token F1 actually measure, which number to fix first, and how to compute them without fooling yourself.
Retrieval and RAG01
Brains Behind the Bots: Classical Planning from Ground Up
PDDL, heuristics that sometimes do nothing, HTN, temporal and multi-agent planning, with real planner numbers on Towers of Hanoi.
AI Foundations10
Classical Planning 101: From STRIPS Blocks to Graphplan Magic
How STRIPS turns a to-do list into an algorithm: factored states, progression and regression, delete relaxation, planning graphs, and modern planners.
AI Foundations09
First-Order Logic Made Friendly: From ‘Socrates Is Mortal’ to Automatic Proofs
Quantifiers, unification, forward and backward chaining, and resolution, from Socrates to a solver that finds the proof for you.
AI Foundations08
Logical Agents 101: Slaying the Wumpus with Pure Reason
Knowledge bases, entailment, resolution and SAT solving, learned by staying alive in the Wumpus World, with runnable PySAT code.
AI Foundations07
Constraint Satisfaction 101: From Sudoku Logic to Map-Coloring Zen
Arc consistency, backtracking with MRV and min-conflicts, explained through Sudoku and map colouring, plus what you would actually use today.
AI Foundations06
Adversarial Search 101: From Minimax to AlphaZero, How AI Plans When an Opponent Fights Back
Minimax, alpha-beta pruning, expectiminimax and MCTS: how a program plans when something is planning against it, and what neural evaluation changed.
AI Foundations05
Beyond Classical Search: Hill-Climbers, Hidden Worlds & Agents That Learn on the Fly
Hill climbing, simulated annealing, belief states and online search: what to do when A* is the wrong tool, the world hides half of itself, or there is no map yet.
AI Foundations04
Intelligent Agents & Search: A Baby-Steps Tour from ‘What is Rational?’ to ‘How do we find the goal?’
What an agent actually is, how to turn a problem into a search problem, and why changing one line of priority code turns breadth-first search into A*.
AI Foundations03
Machine Learning 101: PyTorch, TensorFlow & Decision Trees
What a deep-learning framework actually does for you, how a decision tree picks its questions, and which of the three to reach for on real data.
AI Foundations02
Math for AI Made Simple: The Linear-Algebra Lego Set Behind Every Model
Scalars, vectors, matrices and tensors, the five operations every neural network is made of, and the shape rules that cause most of the bugs.
AI Foundations01
From Chaos to Focus: Understanding Transformers & Attention
Attention and the transformer block from first principles, plus what changed by 2026: pre-norm, RMSNorm, RoPE, grouped-query attention and the KV cache.