Free AI Tutorials and Step-by-Step Workflow Guides

Name the decision, scope, date cutoff, trusted source types, exclusions and required output.

Ask the agent to prefer official data, papers and original documentation, then identify disagreements instead of averaging them away.

For each consequential claim, record the source, publication date and whether the source directly supports it.

Open the original source behind the five claims most likely to change the decision. Remove or qualify anything unsupported.

Tell participants what is recorded, where it is processed and when the audio will be deleted.

Run transcription locally when the recording is sensitive. Correct participant names and domain terms before summarization.

Request decisions, action, owner, due date, supporting timestamp and unresolved questions. Do not infer missing owners.

A participant compares every decision and action against the transcript before copying them into the system of record.

Complete three examples without AI. Capture elapsed time, quality checks and the corrections normally required.

Score correctness, completeness, saved minutes, correction minutes and critical failures. Define what automatically fails a run.

Use ten cases across easy, ordinary and difficult examples. Keep the model, instructions and tool permissions fixed.

Adopt only when net time and quality improve without an unacceptable failure. Otherwise narrow the task, improve controls or stop.

Name required fields, data types, allowed values and which fields may be absent. Do not ask for an open-ended summary.

Retain filename, page, table position and the source text behind every extracted value.

Check dates, identifiers, line-item arithmetic, currency and totals in code. Route any mismatch or low-confidence field to review.

Include scans, rotated pages, missing fields, duplicate documents and layouts from different suppliers before live use.

Start with 20-50 documents you understand. Classify sensitivity and remove files that should not enter the system.

Extract text, tables and headings while retaining filename, page number and a stable link to the original.

Create one isolated workspace, use a local embedding model and confirm that telemetry, backups and model endpoints match your privacy requirement.

Ask ten questions with known answers and three whose answers are not present. Inspect the retrieved passages, not only the final prose.

Use current policy, product documentation and 20 resolved examples. Exclude exceptions that should remain human-only.

Create categories, mandatory escalations and deterministic tools for prices, account state or refunds.

Require the response to cite its governing passage internally and to ask for missing information rather than assume it.

Review correctness, policy fit, tone, data handling and escalation across at least 20 historical cases before live use.

State the current behavior, desired behavior, affected surface and explicit non-goals.

Use a clean branch, run the existing checks and record failures that already exist before the agent edits anything.

Ask it to inspect, plan, edit and test. Require it to stop when evidence is missing or the task expands beyond the contract.

Read the diff, rerun the claimed commands and inspect for unrelated edits, new dependencies and weakened tests.

Use a small repository repair, document extraction or read-only investigation with a frozen input and a deterministic test. Record the clean starting state and expected artifact before either harness sees it.

Use the same model, model settings, task specification, starting files, tool permissions, network rule and time, token and attempt caps. Run each candidate in a fresh worktree, container or disposable folder without production credentials.

Give each harness at least five independent attempts. Save elapsed time, input and output tokens, tool calls, retries, changed files, test results, approvals and the complete transcript; a single lucky pass is not the comparison.

Run the same deterministic checks on every result, inspect unrelated changes and record manual correction time. Compare pass rate, repeatability, total cost, wall-clock time and boundary violations—not polish or confidence.

Adopt only if one candidate improves the named workflow at an acceptable cost and authority level. Otherwise narrow the task, change the test or reject both; do not compensate for weak verification with more retries.

Use a repeated input, a known transformation and a draft output: classify an inbox, prepare a report or update a queue.

Give the workflow the smallest read scope possible. Separate drafting from sending, deleting, buying or deploying.

Record each input, tool call, output and approval. Define completion, timeout, retry and duplicate-prevention behavior.

Run ten representative cases manually, convert recurring failures into rules or tests, then schedule with alerts.

List allowed folders, network endpoints, users and retention. Check telemetry, plugins, backups and fallback providers.

Test a small local model on ten representative cases before buying hardware or adding tools.

For example: search a notes folder and prepare a daily brief. Do not start with email sending, purchasing or shell access.

Put an authenticated browser, companion app or messaging surface in front of the agent. Reach that surface through a private Tailnet or SSH tunnel; keep Ollama, LM Studio, vLLM and retrieval services on loopback or an internal network.

Show whether the model runs on the phone, home host or cloud; record retrieval and tool calls, cap loop length and cost, and keep an obvious way to disable the service and revoke credentials.

Use a local coding agent that can run a small API client. Confirm you can reach the UniFi console without the path you may change, take a current backup and record the Network version. Generate a dedicated API key in Site Manager or the console's Integrations area; prefer a one-month expiry, or set a dated reminder to revoke it.

Start without API access. Redact public IPs, MAC addresses, SSIDs, client names and other identifiers from roaming logs, connectivity failures or RF charts, then ask for a plain-English diagnosis, competing explanations and the next measurement that would distinguish them.

Keep the key in an ignored local .env file—never in chat, source control, command output or a generated dashboard. Put a mechanical wrapper in front of the agent that permits only GET, then inventory sites, devices, clients, networks, Wi-Fi broadcasts, firewall zones and ordered policies. Save a redacted baseline and build dashboards only from that bounded read path.

Have the agent map users, servers, IoT, cameras, guests, management and VPN access into named trust zones. For every proposed VLAN or policy, require source, destination, protocol or service, rule order, business reason, affected dependencies, expected result and rollback. Treat undocumented legacy-firewall objects, NAT, VPN and implicit rules as unresolved—not invitations to guess.

Review the exact API method, URL and redacted body before it runs. Prefer a new disabled policy when supported, keep management access untouched and never batch a firewall migration. After each approved write, re-read live state and test both traffic directions plus DNS, DHCP, admin, VPN and any device-discovery flows the change may affect.

Compare the final state with the plan, preserve the change log without secrets, verify rollback instructions and revoke the project key when the audit or migration ends. Renew a dashboard key intentionally rather than leaving forgotten access active.

Create Inbox, Sources, Notes, Projects and AI Review folders. Each durable note needs a clear title, source link, capture date and status. Use ordinary Markdown and links so the knowledge survives any one app or model.

Parse only allowlisted notes, split Markdown by headings and meaning with Chonkie, preserve each file path and heading, then embed the chunks into a replaceable vector store. Rebuild the index from the vault; never make the index the only copy. Follow the RAG build sequence.

Use retrieval for quotations, arguments and changing source material. If you need stable relationships such as people, projects, systems and ownership, test FaultLine as a separate, correctable fact graph. Require a source note or explicit human confirmation before a fact becomes authoritative.

On a schedule, read new inbox notes, suggest links to existing notes, identify duplicates and draft one synthesis note in AI Review. Persist the last processed file and run result outside the conversation so the next run can resume without guessing.

A separate check confirms every proposed link resolves, every quoted claim points to a source and no canonical note was changed. A person accepts, edits or rejects each draft before moving it into Notes.

At 17:00, let Logic Apps, n8n or another scheduler read the shared calendar and create one work item per appointment. Keep a stable appointment ID, start time, version and status; exclude entries without contact permission or enough data to match the attendee safely.

Have a worker place the call through Azure Communication Services, Twilio or your own PBX and SIP operator. State who is calling and why, disclose automation where required, and offer fixed choices: confirm, cannot attend, repeat or speak to a person. Prefer keypad confirmation; map speech only to those states.

Read the date and time back and require a second explicit answer before changing the booking. Silence, voicemail, low-confidence speech, identity uncertainty or a request outside the script becomes unresolved—never a cancellation.

Query PostgreSQL for the next eligible, opted-in person using your existing priority rules. Atomically create an expiring offer for the open slot, call that person and continue only after decline or expiry. On acceptance, commit the booking and verify the calendar write before ending the call.

Use idempotency keys for appointments, calls and offers so retries cannot cancel or book twice. After each outcome—and once at the end—compare the queue, database and calendar; alert a person about conflicts, failed writes and appointments that remain unconfirmed.

For every turn, keep requester, actor and persona as separate fields. Define explicit modes such as requester credentials, a managed bot or a narrowly approved requester-to-bot fallback. The prompt may propose an action; platform policy chooses the identity.

Use a Slack DM, one team channel or one internal profile—not all three. A sensible first job is incident context gathering: read the thread, retrieve the alert, recent deploy and runbook, then prepare a cited investigation without changing production.

Route the request through an OpenClaw gateway into a per-user or per-persona runtime. Mount identity, instructions, approved skills and gateway configuration read-only. Add gVisor or another tested sandbox, deny-by-default network policy and a workload identity for each service.

Keep long-lived OAuth grants outside the agent. A controlled wrapper validates arguments, checks the requester/actor/persona policy, mints a short-lived token for one capability, redacts the result and emits a structured audit event. Route models separately through managed Vertex AI or a self-hosted Ollama endpoint when the workload justifies it.

Before a write, restate the intended actor, target and change; require confirmation for production, access, paging and external communication. Record the policy decision, fallback identity, confirmation and downstream response in searchable audit storage or the organization's SIEM.