Agentic AI on RoboSathi

What Is an AI Agent?

Fri, 16 Oct 2026 00:00:00 +0000

Playlist Coming Soon !

Most definitions of an “AI agent” describe what the agent can do: perceive, reason, call tools, pursue a goal. These notes argue that this is only half the picture. For any agent that acts in the real world, the more important question is who decides what it may do, and where that decision is enforced.

Levels of Automation

Fri, 16 Oct 2026 00:00:00 +0000

Playlist Coming Soon !

“Is your agent autonomous?” is one of the most common questions asked about AI agents, and one of the least useful. Real systems are autonomous for some decisions, supervised for others, and fully manual for a few, often within a single conversation. These notes replace the yes/no question with a vocabulary borrowed from human factors engineering, a field that has studied the division of work between people and machines since the 1950s, in aviation, process control and undersea robotics.

Workflow Design Patterns

Fri, 16 Oct 2026 00:00:00 +0000

Playlist Coming Soon !

A surprising amount of what is marketed as “Agentic AI” is, structurally, a workflow: a sequence of steps fixed in code, in which a language model does some of the work but never decides what happens next. That is not a criticism. Workflows are predictable, testable and cheap, and most production systems should be mostly workflow.

Agentic Design Patterns

Fri, 16 Oct 2026 00:00:00 +0000

Playlist Coming Soon !

The previous notes described systems in which code chooses every next step. Here we hand some of those choices to the model. A pattern is agentic when the model decides at least one of three things: what to do next, whether the work is good enough, or how to split the work up.

We study six agentic patterns in increasing order of the control they hand over: a tool-use loop, ReAct, reflection, evaluator–optimizer, planning, and orchestrator–subagent. The thread running through them is that every decision handed to the model needs a fence around it, and the fence is the part the engineer is responsible for.

Retrieval-Augmented Generation

Fri, 16 Oct 2026 00:00:00 +0000

Playlist Coming Soon !

A language model knows a great deal about language and the world as it was during training, and nothing about your business: your refund policy, your product catalogue, last week’s price change. Retrieval-Augmented Generation (RAG) closes that gap by looking up relevant passages at query time and placing them in the model’s context, so the answer is grounded in your data.

Type Safety, Loop Control & State

Fri, 16 Oct 2026 00:00:00 +0000

Playlist Coming Soon !

An agent can go off the rails in three distinct ways. It can produce output of the wrong shape: a tool call with a missing field, JSON that doesn’t parse, an amount written as a string. It can run too long or in circles: the same call five times, a loop that never converges, a budget that quietly disappears. Or it can die halfway: a crash, a deployment or a person pressing Stop in the middle of a refund.

Context Management

Fri, 16 Oct 2026 00:00:00 +0000

Playlist Coming Soon !

A language model has no memory between calls and no access to the world beyond the text it is given. On every call, its entire world is its context window. Deciding what goes into that window, in what order and at what size, is therefore one of the most consequential design decisions in an agent, and one that is repeated on every turn of the agent loop.

Memory Management

Fri, 16 Oct 2026 00:00:00 +0000

Playlist Coming Soon !

Context management decides what a model sees on one call; memory decides what survives between calls. An agent that remembers can offer continuity, learn from repeated situations and avoid asking the same questions twice. But what an agent remembers is also what it will act on later, which makes memory an attack surface and a privacy obligation as much as a feature.

Hallucination Checks

Fri, 16 Oct 2026 00:00:00 +0000

Playlist Coming Soon !

A schema can guarantee that a reply has the right shape. It cannot guarantee that what the reply says is true. A perfectly formed sentence such as “your refund of $118.84 has been issued” is a serious failure if the refund is actually waiting for review.

These notes define a hallucination precisely for an agent (a claim not supported by what the turn actually observed), explain why it is costly, and develop a two-level check that runs after the model writes and before the user reads: cheap token-confidence signals from log-probabilities, and grounding of each atomic claim against evidence, using deterministic record checks and natural-language inference.

LLM as a Judge

Fri, 16 Oct 2026 00:00:00 +0000

Playlist Coming Soon !

Many of the qualities we care about in an agent’s output have no deterministic test: is the explanation accurate, are the trade-offs stated, is the tone right? People can judge these, but slowly. A language model can judge thousands of outputs in minutes. The catch is that a judge is itself a model, with biases, drift and its own hallucinations.

Agent Security Principles

Fri, 16 Oct 2026 00:00:00 +0000

Playlist Coming Soon !

An agent combines things that are each manageable alone and dangerous together: access to private data, exposure to untrusted text, and the power to act. Because a model cannot reliably tell instructions from data, any text it reads can steer what it does. The consequence, and the theme of these notes, is that the defences cannot live in the model; they must live in the harness.

Evals

Fri, 16 Oct 2026 00:00:00 +0000

Playlist Coming Soon !

Every earlier chapter of this course made a claim about the system: no refund over the limit, no claim without evidence, no other customer’s data. Evals are how those claims are checked, on every change, against a real model.

Evals are not tests. Tests check that code does what it says, deterministically and in seconds; evals check that a non-deterministic system of model and harness behaves well on realistic cases and attacks, slowly and at a cost. These notes set out the principles that make an eval worth trusting, three kinds of grader, two open-source frameworks, and the design of an eval harness people will actually run.

Observability & Analytics

Fri, 16 Oct 2026 00:00:00 +0000

Playlist Coming Soon !

A non-deterministic agent cannot be reproduced; it can only be recorded. The same input may take a different path tomorrow, so if a turn was not recorded when it happened, it is gone. Observability is the practice of recording enough, in the right shape, to answer three different questions: what happened in this turn, why it happened, and how the whole fleet is doing.

Model Context Protocol

Fri, 16 Oct 2026 00:00:00 +0000

Playlist Coming Soon !

Every AI application that wants to use a tool or a data source needs an integration with it. Without a standard, that is one bespoke integration per pair of application and tool. The Model Context Protocol (MCP) replaces those pairwise integrations with one open protocol between AI applications and the systems they use.

These notes cover the protocol’s architecture and primitives, its security model (the protocol connects but does not decide trust), a worked example of an analytics server used by an operations agent, a client that governs every server’s tools through its own configuration, and what it takes to move a server from a local subprocess to a shared HTTP service.

System Design Patterns

Fri, 16 Oct 2026 00:00:00 +0000

Playlist Coming Soon !

The model is the least reliable component of an agent, and it is surrounded by networks, quotas and databases that fail too. A single turn may make twenty calls; if each succeeds 99% of the time, one turn in five meets a failure somewhere. At scale, failure is not an exception to handle occasionally; it is the normal case to design for.

Build vs Buy

Fri, 16 Oct 2026 00:00:00 +0000

Playlist Coming Soon !

This course built a gatekeeper, guardrails, memory governance, hallucination checks and an evaluation harness. Should a production team build all of that? Mostly not. Some of it, absolutely. These notes give the tools to tell which: a per-component framing with four options (build, adopt, buy, partner), the arithmetic of ROI, payback, NPV, total cost of ownership and break-even volume, and the non-financial factors that often decide the matter.