2.8 Appendix: How the AI Work System Runs
This appendix is not required for daily use. Its purpose is diagnostic: when a result misses, you can tell which layer failed instead of rephrasing the request.
Start with the attribution table below and check the most likely layer first.
| Symptom | Layer to check first |
|---|---|
| Fluent answer, wrong facts or figures | The model and the input material |
| Forgot what was already stated | Context and the workspace |
| Knows what to do but cannot execute | Tools, authorization, and permissions |
| The same task is done differently each time | The Skill's steps and constraints |
| Cites an outdated policy or old price | The knowledge base and Memory |
| A flow that should be fixed improvises every time | The choice between workflow and agent |
The Model: Generate Content from Input
A large language model learns patterns of language and knowledge from a corpus and generates subsequent content from its input. Summarization, rewriting, extraction, and code generation use this mechanism.
For internal material, supply the files or data and specify the version to use. To compare a summary with its source, ask:
Context: How Much It Can Process at Once
A token is the basic unit the model processes; it is not a word. A character may be one or more tokens, and code and punctuation are counted differently. The context window is the total input, conversation history, and output a single inference can hold.
The input for a task consists of its goal, current material, and relevant history. Store long-term material separately and reference it as needed:
Where things belong: stable material in Library, structured data in Base, long-term rules in Memory, and the process of one piece of work in a workspace. The system retrieves what it needs instead of holding everything in one conversation.
Prompts: A Task Brief
A prompt carries the goal, background, material, constraints, examples, and expected output. Its quality is not a function of length but of whether it is sufficient to execute and to verify.
| Element | What it answers |
|---|---|
| Goal | Which problem is being solved |
| Input | Which material or systems are involved |
| Action | Analyse, organize, generate, or rewrite |
| Constraints | What must not change, which standards apply |
| Output | Which file or structure to deliver |
| Verification | What counts as correct and usable |
Input: "Supplier Docs/2026ss-tech-pack.pdf" in Library.
Action: extract fabric, certification, and delivery terms.
Constraints: use only the document's content; add no outside knowledge.
Output: a one-page Markdown brief with a page number for every conclusion.
Verification: each conclusion can be traced to a page in the source.
From a prompt to a capability, there are four levels:
| Level | Form | Fits |
|---|---|---|
| Prompt | How to do it this time | One-off tasks |
| Task card | A fillable fixed structure | Repetitive tasks with fixed fields |
| SOP | Fixed steps, roles, checkpoints, and exception handling | Processes that get handed over |
| Skill | A packaged SOP with scripts and resources, ready to run | Long-term reuse |
Not every prompt deserves packaging. Run it successfully three to five times, confirm the method is stable, then invest in packaging.
The Agent: A Loop Around a Goal
An agent does not "answer once". It runs a loop: receive the goal, observe material and state, plan the next step, call tools, read results and errors, then decide whether to finish, pause, or continue.
In practice the loop branches, retries, or pauses; it is not a straight line.
| Dimension | Chat mode | Agent |
|---|---|---|
| Core action | Generate a response | Plan, call tools, execute, deliver |
| Scope | The current conversation | Files, tools, systems, task state |
| Process | Usually one pass | Multiple rounds of observation and action |
| Execution | Generate content | Call tools and process returned results |
| Control | Prompt and review | Permissions, checkpoints, logs, rollback |
Tools and Connectors: Knowing vs Doing
A tool is a concrete capability the agent can call: read a file, run a search, generate a spreadsheet, send a message. A Connector is a preconfigured external service connection that requires authorization.
The agent can explain how to send an email, but it can only draft or send one after the mail Connector is installed and authorized. It can write SQL, but it can only query the database after the database Connector is installed and authorized.
So when a task fails, the order of investigation is: is the tool connected and authorized → does the permission scope cover the target data → is the data somewhere it can reach. "Is it smart enough" is rarely the first question.
Skills: Fixing the Process
A Skill is not a smarter model. It is a set of instructions, scripts, knowledge, and templates organized around one class of task, so execution stays consistent.
Its value is not "making the model stronger" but locking down the steps that are easy to get wrong or skip. Give the same batch of invoices to a model ten times and you may get three approaches; give it to a Skill and all ten runs follow the same verified path.
invoice-skill/
├── SKILL.md # Triggers, steps, boundaries, output
├── references/ # Fields, categories, business rules
├── scripts/ # OCR, validation, table processing
├── templates/ # Excel and report templates
└── tests/ # Normal and edge-case samplesSKILL.md is the entry point: when to use it, how to execute, where the boundaries are. References hold business knowledge, scripts hold the running code, templates keep output consistent, and tests cover edge cases.
| Comparison | Prompt | Skill |
|---|---|---|
| Scope | The current conversation | Reuse across tasks |
| Carries | Text | Instructions, scripts, resources, templates |
| Loading | Enters context directly | Loaded on demand |
| Consistency | Depends on how clearly this run was written | The same path every time |
Read the Skill's SKILL.md, scripts, and templates, then configure the external services and execution environment listed there.
MCP: A Standard for Tool Access
MCP (Model Context Protocol) defines how an AI client discovers and calls external tools, reads resources, or retrieves prompt templates. It standardizes access; it does not change what the tool can do.
It solves an integration-count problem: without a common standard, every AI product builds an adapter for every system; with MCP, a provider exposes its capability once and every MCP-capable client can call it.
API and MCP
An API is an interface between systems, for example querying data or creating a record over HTTP. An MCP server calls one or more APIs internally and exposes them as tools.
With direct API calls, the caller handles authentication, parameters, errors, and rate limits. With MCP, the server organizes those interfaces as tools that clients can discover and call.
Knowledge Base, RAG, and Memory
These provide different kinds of context:
| Concept | What it stores | How it is used |
|---|---|---|
| Conversation context | The current task discussion | Carry forward requirements and intermediate results |
| Knowledge base / RAG | Searchable facts and references | Retrieve relevant passages and cite sources |
| Memory | Preferences and long-term rules | Apply personal settings in later tasks |
A knowledge base holds policies, product material, cases, and SOPs for retrieval.
RAG (retrieval-augmented generation) finds relevant passages and supplies them to the model to compose an answer. File versions, chunking, metadata, and search terms determine the passages returned. Source references let you open the original material for further reading.
Memory holds preferences and long-term rules. When a working habit or rule changes, enter the new requirement on the 【Memory】 page.
Workflow and Agent: Who Decides the Path
They are not substitutes; they are two ways of organizing action.
| Dimension | Workflow | Agent |
|---|---|---|
| In one line | A standardized production line | An executor that works toward a goal |
| Path | Fixed at design time | Determined at run time |
| Decision point | Design stage | Execution stage |
| Controllability | High, easy to predict and roll back | Lower, paths may vary |
| Debugging | Step-by-step tracing | Requires logs and intermediate state |
| Fits | Clear steps, repeatable, high compliance | Unclear path, needs environmental feedback, open goal |
Workflows fit: fixed SOPs (ticket received → classify → assign), batch processing (compress and watermark 100 images), approvals that need step-by-step audit, reports that must be regenerated the same way.
Agents fit: a clear goal with an unclear path (research competitors and produce a comparison), tasks that need several tools explored, environments that change, open-ended work that cannot be written as fixed steps.
Three common misjudgements:
- Assuming an agent is always better than a workflow. For deterministic tasks a workflow is more stable, cheaper, and easier to audit.
- Assuming a workflow cannot be intelligent. Workflow nodes can call a model to summarize, classify, or extract; the model makes judgements and the flow decides the route.
- Assuming more autonomy is better. More freedom makes failures harder to diagnose; complex systems usually let an upper agent decide and hand stable subtasks to a workflow.
How they nest: an agent writes stable subtasks as fixed processes (a Skill backed by a workflow) and decides only where uncertainty remains; a workflow's judgement node hands unstructured input to an agent.
See these mechanisms in use in the existing demos: Connector Authorization, Knowledge Retrieval, and Create and Run a Workflow.
Summary
The model generates, tools execute, Skills fix the method, the knowledge base supplies evidence, workflows fix the path, and Memory together with the workspace maintains continuity.
2.7 Base in Depth: Views, Fields, and Sharing Permissions
Lesson 1.8.2 covered what Base is. This one covers using it well — view choice, field design, and permission boundaries.
3.1 Email Management & Structured Follow-ups
You get 10+ supplier emails a day, each with a Tech Pack PDF, product images, or a quote.