Read our operating thesis — Machines work better in tandem

Blog

Notes on coordinated intelligence — how autonomous systems earn operational trust.

JULY 2026  ·  OPERATING THESISFEATURED

Machines work better in tandem

Models can reason. Tools can act. The missing layer is the system that coordinates both — while keeping people informed, accountable and in control. Our founding argument, in full.

Read the thesis  →
JULY 2026PROCUREMENT

Agent washing: how to tell a real agent from an AI wrapper

Half the products sold as AI agents are a chatbot with a system prompt. Here is a test battery you can run in a demo — five questions whose answers separate a real agent from a wrapper, no matter what the marketing says.

Read  →
JULY 2026PATTERNS

AI agent design patterns: ReAct, plan-and-execute, and reflection

The three core agent patterns are not interchangeable — each makes a different bet about when the model should think, act and check. Here is what each is for, and the failure each one is quietly prone to.

Read  →
JULY 2026RETRIEVAL

Agentic RAG: retrieval with a decision loop

Classic RAG retrieves once and answers. Agentic RAG lets the model decide what to retrieve, judge whether it got it, and try again — which turns retrieval failures from a dead end into something that compounds.

Read  →
JULY 2026ARCHITECTURE

Context engineering: the discipline that replaced prompt engineering

Prompt engineering is writing good instructions. Context engineering is deciding what occupies a finite window and what it costs — and once you understand the KV cache, prefix stability stops being a style choice and becomes an economic one.

Read  →
JULY 2026SECURITY

A prompt injection catalogue: working examples and what stops each

One entry per attack: the payload, the channel it arrives through, what it achieves against an agent that can act, and the control that actually stops it — which is never a filter.

Read  →
JULY 2026CORRECTNESS

Race conditions in agent loops: parallel tool calls and the state you didn't lock

Agents emit parallel tool calls by default, and a language model has no concept of a transaction boundary. Two calls in one turn can write the same row — and the pattern you chose determines which races you get.

Read  →
JULY 2026EVALUATION

Calibrating an LLM judge: inter-rater reliability for model-graded evals

An uncalibrated LLM judge is an opinion with a decimal point attached. Measure agreement with Cohen's κ before you trust it — and measure your humans against each other first, because that is the ceiling.

Read  →
JULY 2026ARCHITECTURE

What are agentic workflows — and when a workflow beats an agent

If you can enumerate the steps in advance, you have a workflow — and a workflow is cheaper, testable, auditable and incapable of surprising you. Most systems sold as agents are workflows, and most teams should build one.

Read  →
JULY 2026ECONOMICS

After-hours answering: the unit economics of never missing a call

After-hours answering is not a cost-reduction case, it is a revenue-recovery case — and that changes the arithmetic completely. Here is the model, the break-even containment rate, and the cases where the honest answer is that it does not pay.

Read  →
JULY 2026GOVERNANCE

Agent authority as code: writing the boundary in Rego

An agent is not a principal — it is a delegate. That single fact makes role-based access control the wrong model, and it is why authority has to be expressed as policy evaluated on the tool call rather than as a sentence in a prompt.

Read  →
JULY 2026RUNTIMES

Hermes Agent vs OpenClaw

This is not a symmetric comparison. Hermes ships a first-party `hermes claw migrate` command that imports OpenClaw's memories, skills and config — which tells you more about how these two relate than any feature table.

Read  →
JULY 2026VOICE

The voice agent stack: latency, turn-taking and barge-in

Your voice agent's response time is dominated by how long it waits to decide you stopped talking, not by inference. That is a configuration decision, and it is the one that makes a call feel human or not.

Read  →
JULY 2026FRAMEWORKS

Mastra vs LangGraph vs CrewAI

The three differ on one axis: what they force you to make explicit. A team, a state machine, or a TypeScript application. Plus the LangGraph resume behaviour that will duplicate your side effects if you haven't read the tests.

Read  →
JULY 2026COST

Semantic caching for AI agents

Semantic caching is designed for repeated questions, and an agent loop almost never repeats a prompt. The wins are on the tool side — and the cache key has to carry the requester's authorization scope, or the cache becomes a data-leak channel.

Read  →
JULY 2026DATA

Choosing the agent data layer: pgvector vs Chroma vs Pinecone

Start in Postgres. Here are the specific thresholds where that stops being true, why an agent's retrieval pattern argues for co-location, and why your recall problem is almost certainly chunking rather than the database.

Read  →
JULY 2026OBSERVABILITY

Agent observability: Langfuse vs Arize Phoenix vs Braintrust

Before choosing a tool, decide what a trace has to contain to answer “why did it do that?”. Then one architectural question — OpenTelemetry-native or proprietary SDK — narrows the field faster than any feature matrix.

Read  →
JULY 2026ARCHITECTURE

The AI agent tech stack: seven layers

Most stack diagrams stop at the control loop. The two layers after it — governance and evidence — are what separate an agent you demo from an agent you deploy, and they are architecture, not process.

Read  →
JULY 2026RELIABILITY

Idempotency for AI agent actions

A retried HTTP request is a duplicate. A retried agent action is a second refund. Every idempotency pattern you know assumes a client that repeats itself exactly — an agent does not, and that breaks the key.

Read  →
JULY 2026ENGINEERING

Building production agents with the Claude Agent SDK

The SDK is Claude Code as a library. This is the part the quickstart skips: the six-step permission evaluation order, the three ways your approval callback gets silently bypassed, and what a subagent actually inherits.

Read  →
JULY 2026SECURITY

Agentic AI security: a working threat model

An agent with tools turns a prompt injection into a transaction. The threat model for systems that can act, the three conditions that make exfiltration possible, and the controls that hold when the model is fooled — because it will be.

Read  →
JULY 2026DEFINITIONS

Agentic AI vs generative AI vs AI agents

Three terms, used interchangeably by people who should know better. Here is what each one actually denotes, why the major vendor definitions contradict each other, and the two questions that tell you which you are dealing with.

Read  →
JULY 2026DELIVERY

What is a forward-deployed engineer?

The role Palantir invented and every serious AI-agent company is now hiring for — what an FDE actually does, how the job differs from solutions engineering and professional services, and why agent products cannot be delivered without one.

Read  →
JUNE 2026COORDINATION

When should an agent ask?

Designing the authority boundary between machine execution and human judgment.

Read  →
JUNE 2026CONTROL

Evidence is the interface

Why every agent action should leave a record a person can review — and what that changes about trust.

SOON
MAY 2026SYSTEM

One objective, four stages

Direct, coordinate, execute, verify — the anatomy of a Tandem run, from instruction to verified outcome.

SOON
MAY 2026PERSPECTIVE

The case against parallel tools

A drawer full of disconnected copilots is not an operating system. Why coordination is the unit of value.

SOON

Follow the work.

One essay a month on coordination, control and operational AI. Nothing else.

By subscribing, you agree to the Tandem Privacy Statement.