BotCurrent↗
← Back to examples

Proposed · Not tested

Makers discover suitable markets after applications close

Extension of source-backed task: Shortlist industry events into practical trip options. This is not an additional source-backed job.

Proposed · Not tested. This is an original editorial plan. Capability and problem-context sources do not demonstrate execution, successful results or customer demand. Platform compatibility is unknown and untested.

The problem

Vendor opportunities are scattered and differ in eligibility, dates, fees and application deadlines.

Agent job

Review a bounded list of official opportunities; record deadline, eligibility, fee and source timestamp; flag unknowns; rank fit without claiming acceptance or sales potential.

Expected output

Original short regional opportunity brief with source links, deadlines and a suitability explanation; no copied listings or photos.

Why an agent / simpler alternative

Assessment

The agent can compare messy eligibility and application language against a maker’s constraints and explain uncertain fit. Official newsletters or a calendar are better if they already cover the niche. Human checking is essential because deadlines, fees and availability change and low-priced personalization can be uneconomic.

Setup requirements

Items
  1. One defined region, product category, travel radius and buyer budget

  2. Bounded list of official organiser pages or licensed feeds

  3. Manual review cadence and a clear checked-at timestamp

  4. Rights-aware original summary format; no automated scraping, application submission or copied photos

Inputs and access

  1. Name

    Maker’s non-sensitive product category and travel radius

    Source or owner

    Prospective consenting customer or specified official publisher

    Sensitivity

    Use synthetic, public or appropriately deidentified material; confirm actual sensitivity before work

    Permission needed

    Owner authorizes scoped access and processing; verify rights and retention before receiving files

  2. Name

    Official organiser application pages or licensed feeds

    Source or owner

    Prospective consenting customer or specified official publisher

    Sensitivity

    Use synthetic, public or appropriately deidentified material; confirm actual sensitivity before work

    Permission needed

    Owner authorizes scoped access and processing; verify rights and retention before receiving files

  3. Name

    Owner-set venue and budget filters

    Source or owner

    Prospective consenting customer or specified official publisher

    Sensitivity

    Use synthetic, public or appropriately deidentified material; confirm actual sensitivity before work

    Permission needed

    Owner authorizes scoped access and processing; verify rights and retention before receiving files

Proposed steps

  1. Agree category, geography, timing and exclusions; check whether a free source already meets the need.

    Expected output: Buyer-fit brief

    Approval gate: Do not imply that paid research guarantees acceptance or sales.

  2. Select a small allowed source list and inspect terms and access limits.

    Expected output: Source register

    Approval gate: Stop on restrictions; do not bypass blocks or collect private contact data.

  3. Extract application deadline, event dates, eligibility and disclosed fee from official pages.

    Expected output: Dated fact sheet with field-level links

    Approval gate: Missing values remain unknown; do not infer fee totals.

  4. Exclude closed or unsuitable opportunities and explain fit for the remaining entries.

    Expected output: Shortlist with inclusion/exclusion reasons

    Approval gate: Unclear eligibility is a question for the buyer, not a presumed match.

  5. Human-recheck each shortlisted deadline and fee and write original concise summaries.

    Expected output: Reviewed 5–10-entry brief

    Approval gate: No copied marketing text/photos or promise that places remain available.

  6. Deliver the dated brief with unknowns and direct application links; record the freshness limit.

    Expected output: Buyer-facing brief and corrections policy

    Approval gate: Buyer chooses applications and pays organisers; no outreach, submissions or standing monitoring without approval.

Synthetic output illustration — not an executed result

Synthetic

Yes

Executed

No

Text

SYNTHETIC: Fictional Riverside Makers Day: ceramics accepted; application deadline 15 November; fee unknown; travel fit yes; status VERIFY FEE. Source placeholder: organiser page required. This fictional entry must never be shipped as a real opportunity.

Human approval boundaries

  1. Human verifies dates, terms and summary originality before delivery; maker alone decides applications and payments. No submissions, outreach or automated scraping.

  2. Human service provider reviews quality, scope and quoted fee; customer approves contract, delivery recipients and payment terms. Separately approve purchases, credentials, publication and external sends. No commitments or payments are made in this research.

Failure modes

  1. Applications may close early

  2. Fees exclude extras

  3. Eligibility can be ambiguous

  4. A free organiser newsletter may satisfy the same need

  5. Manual freshness checks can exceed the fee

Recovery and troubleshooting

Items
  1. If a deadline changes before delivery, replace or remove the opportunity and refresh the checked-at time.

  2. If the organiser page is unavailable, mark the entry unverified and exclude it from actionable recommendations.

  3. If the niche yields too few suitable entries, report that honestly and re-scope or decline the offer rather than padding the brief.

Unexecuted validation plan

Sample setup

Check five official organiser pages manually; include one closed opportunity and one missing fee as deliberate exclusions/unknowns.

Acceptance checks
  1. Every actionable entry has official link and checked date

  2. No guessed deadlines or fees

  3. Closed entries excluded

  4. Respect site terms; stop on restrictions

  5. Human rechecks before delivery

Stop conditions
  1. Stop if data authority or rights are unclear.

  2. Stop if critical seeded failures are missed; do not claim readiness.

  3. Stop if manual correction time exceeds the pilot effort budget without customer approval.

Executed

No

Costs and effort — unknown or hypothetical

Status

unknown_or_estimate

Currency

CAD

Items
  1. Agent subscription/API usage: not quoted; verify current plan and commercial data terms.

  2. Human intake, rights review, QA and revisions: unknown until timed pilot.

  3. Storage, hosting, integration and payment-processing costs: excluded unless separately agreed.

  4. Customer acquisition and support time: not measured.

Caveat

No margin or income estimate. Price hypotheses are editorial offer tests, not observed market rates; taxes, scope and effort require a real quote.

Proposed service concept — earnings not verified or guaranteed

Buyer

Independent craft maker in one defined region and product category

Deliverable

Original short regional opportunity brief with source links, deadlines and a suitability explanation; no copied listings or photos.

Charging basis

Small paid research brief or opt-in niche digest; sell original filtering and verification rather than republishing source content.

Acquisition channel

Permission-based discovery with existing professional contacts, referrals or an opt-in sample page; none executed.

Assumptions
  1. Customer has this unresolved problem and values a reviewed deliverable above existing built-in alternatives.

  2. A consenting pilot confirms data access, achievable quality and economically tolerable review time.

  3. Provider can deliver within a written scope and supports the result.

Revenue guarantee

No

Canadian adaptation — proposed

Proposed Canadian pilot: start with one specified province and travel radius, use the organiser’s local deadline timezone and show CAD fees only when explicitly stated. Distinguish provincial or residency eligibility from assumptions and keep unknown fee extras visible. BC sources are starting points, not proof of open applications, nationwide coverage or sales potential.

Limits

  1. Original proposed plan; untested.

  2. Problem and capability references are evidence of context only, not demonstrated end-to-end success, customer demand, willingness to pay or profitability.

  3. Compatibility, workload, delivery effort and availability must be verified in a real authorized pilot.

  4. Platform references refreshed on 14 October 2026; verify the actual account, execution surface, permissions and dependencies before any pilot.

Context and capability sources

These links support context or possible capabilities, not completion of this plan. Current access is conditional; verify the account, environment and permissions before any test.

https://craftcouncilbc.ca/call-for-entry/ ↗
Problem context only; frequency, buyer demand and this workflow are not validated.

https://support.claude.com/en/articles/13345190-get-started-with-claude-cowork ↗
Current general capability context only; exact workflow compatibility and execution remain untested.

https://support.claude.com/en/articles/16761823-claude-cowork-and-chat-are-one-claude ↗
Current general capability context only; exact workflow compatibility and execution remain untested.

Candidate platforms — compatibility untested

  1. Name

    Claude (Cowork capabilities)

    Required capabilities
    1. Authorized browser research plus editable report creation; exact account/browser compatibility untested.

    Capability source urls
    1. https://support.claude.com/en/articles/13345190-get-started-with-claude-cowork

    2. https://support.claude.com/en/articles/16761823-claude-cowork-and-chat-are-one-claude

    Workflow compatibility

    Unknown; verify in the proposed first test.

    Historical candidate name

    Claude Cowork

    Selection basis

    Editorial candidate from general capabilities; exact end-to-end fit untested.