# AX Check: nestenius.se Checked 2026-09-22. This is a personal blog, not a priced product agents can buy. Docs index and code snippets are easy to find, but no quickstart, install guide, or pricing page exist for a purchasable product. ## End-to-end onboarding not demonstrated ## Coding sessions All three sessions completed but could not find pricing since none exists for this blog. Two said no pricing applies; one instead priced an unrelated open-source library mentioned in a post, noting it is free under its license with paid add-ons nearby. ### DeepSeek V4 Pro [View public run](https://agents.withgauge.com/p/runs/c2af4e88-99b4-413b-bd1e-29bce0b7f3d4) · [Read transcript](https://www.ax-check.com/nestenius.se/sessions/deepseek.json) Final output (seq 51) explicitly states 'there is no product pricing to report' — it describes consulting being 'quoted per engagement' but gives no actual cost figure tied to plan/region/machine-size/workload assumptions, so no price was stated. #### End-to-end onboarding - **End-to-end onboarding not demonstrated**: No credentials were obtained or used, and no authenticated product operation was attempted. The agent determined early via web research that 'Tore Nestenius' refers to a consultant/trainer and his company site (a WordPress marketing page), not a hosted SDK or API product, so it never reached an onboarding or credential step. Event 51: ```text there's nothing for me to build against or manage. It has no hosted SDK/API and no public developer workflow. ``` #### Hallucinated URLs None identified in this transcript. #### Blockers - **No developer product exists for the requested subject**: The agent researched 'Tore Nestenius' via GitHub, Wikipedia, and web search, then fetched the tn-data.se site directly and found it to be a WordPress consulting/training marketing page for an independent .NET/Azure consultant, with no SDK, API, or pricing tiers. This is not agent error or a credential/environment issue -- it is a mismatch between the seed prompt's premise (a 'product' to build an example with) and reality, correctly identified and reported rather than fabricated. Event 51: ```text "Tore Nestenius" is not a software product — it's a person and a consultancy. ``` Event 51: ```text There is no product pricing to report. There's no API, no SDK, no metered/seat-based SaaS tiering. ``` #### Suggested Changes None identified in this transcript. ### Kimi K3 [View public run](https://agents.withgauge.com/p/runs/369006a5-253f-4bde-9e30-d407ace97307) · [Read transcript](https://www.ax-check.com/nestenius.se/sessions/kimi.json) Final output explicitly states pricing is 'Not applicable' with no figure or assumptions given — it never states what the product would cost. #### End-to-end onboarding - **End-to-end onboarding not demonstrated**: Agent made a single sanity check (npm/pip search) confirming no package exists under this name, then stopped per explicit instructions. No product credentials were sought or used since no actual product was identified to onboard into. Event 3: ```text npm search nestenius 2>&1 | head -5; echo "---"; pip index versions nestenius 2>&1 | head -3 ``` #### Hallucinated URLs None identified in this transcript. #### Blockers - **Requested subject is a person, not a product**: The seed prompt asked the agent to build an example using 'Tore Nestenius', but this is a named individual (a consultant/trainer), not a software product with an SDK or API. This is neither a product defect nor an agent error -- it's a mismatch between the task input and reality. The agent verified this via package registry searches before halting, matching the instruction to stop plainly if no developer workflow exists. Event 4: ```text No matches found for "nestenius" --- ERROR: No matching distribution found for nestenius ``` Event 6: ```text "Tore Nestenius" is not a product, so there is no developer workflow I can act on. ``` #### Suggested Changes None identified in this transcript. ### Qwen 3.8 Max [View public run](https://agents.withgauge.com/p/runs/6c2596a8-00ab-41b5-9b0f-0bd08f5326ca) · [Read transcript](https://www.ax-check.com/nestenius.se/sessions/qwen.json) Final output states OpenIddict costs nothing under Apache-2.0 (no tiers/fees/license key) and names the basis — license type — while flagging two adjacent paid add-ons (Volo.OpenIddict.Pro, Rock Solid Knowledge SAML2P) and explicitly disclosing it did not confirm their prices, rather than inventing a number. #### End-to-end onboarding - **End-to-end onboarding not demonstrated**: The agent never attempted any credentialed product operation. It determined early that "Tore Nestenius" is a person (a blogger/consultant) rather than a product, and that the likely intended subject, OpenIddict, is a self-hosted open-source library with no hosted API or SaaS surface to authenticate against. No credentials were requested, obtained, or used, and no authenticated operation was attempted. Event 35: ```text There is no hosted service, SDK, or API named "Tore Nestenius" to call, so there's nothing I can point an example at. ``` Event 35: ```text There's no hosted endpoint, no API key, and no CLI workflow I can act on remotely, so I'd have to violate your "stay light" instruction to produce anything runnable. ``` #### Hallucinated URLs None identified in this transcript. #### Blockers - **No hosted product exists behind the requested name**: The seed prompt asked to build an example using "Tore Nestenius," but that name refers to a person (a .NET consultant/blogger), not a product with an SDK or API. This is a task-framing issue rather than a product or agent defect: the agent correctly identified there was nothing to call and stopped instead of fabricating an integration. Event 35: ```text "Tore Nestenius" is a person, not a product.** He's a .NET developer/consultant and Microsoft MVP who writes widely-read guides on OpenIddict ``` - **Intended library requires a local .NET stack the session rules forbid**: The closest real candidate, OpenIddict, is a self-hosted framework needing a custom ASP.NET Core authorization controller and a running server to exercise OAuth2/OIDC flows -- this conflicts with the seed prompt's explicit instruction to avoid local service stacks or long-running commands. This is a product-nature/environment mismatch, not an agent error, and the agent stopped as instructed rather than violating the constraint. Event 35: ```text OpenIddict is explicitly *"not a turnkey solution but a framework that requires writing custom code"* (their own README wording — you must write at minimum an authorization controller). ``` Event 35: ```text You ruled out both. There's no hosted endpoint, no API key, and no CLI workflow I can act on remotely, so I'd have to violate your "stay light" instruction to produce anything runnable. ``` - **No .NET toolchain available in sandbox**: Even setting aside the local-stack restriction, the sandbox environment lacks a .NET SDK, which would be required to build or run any OpenIddict example. This is a test-environment limitation. Event 16: ```text /bin/bash: line 1: dotnet: command not found ``` #### Suggested Changes None identified in this transcript. ### Task given to each agent Help me build a simple example using Tore Nestenius. Tell me how pricing works, and briefly tell me whether this product will be easy for you to manage. Let me know if you get blocked. If this product has no developer workflow you can act on, say so plainly and stop. Stay light: use the hosted product through its SDK or API. Do not start local service stacks or wait for long-running commands; if the quickstart requires either, say so plainly and stop. No product credentials were supplied and no purchases were authorized. ## Score: B · 73/100 (provisional) Grades come from completed site checks. Coding sessions and skipped checks do not affect the score. ### Clarity - **Failed** — Homepage answers Markdown requests ```text Homepage returned text/html for a text/markdown request; no Markdown representation offered. ``` - **Pass** — llms.txt provides an actionable documentation index ```text llms.txt lists About, Services, RSS, sitemap and categorized post indexes with descriptions. ``` - **Pass** — llms.txt provides navigation guidance ```text llms.txt explains URL shape /{category}/{slug}/ and links home, RSS and sitemap. ``` - **Skipped** — llms.txt mentions offered API, MCP, and skills ```text llms.txt describes a personal blog; no API, MCP server or skills are offered to mention. ``` - **Pass** — A compact guide representation exists ```text llms.txt is a compact Markdown guide to the blog's posts and sections. ``` - **Pass** — A focused guide is directly retrievable ```text llms.txt fetched directly at /llms.txt as text/plain Markdown. ``` - **Pass** — Equivalent instructions fit a token budget ```text llms.txt is 3125 tokens, well under the 8000-token budget. ``` - **Skipped** — Product-docs links survive format changes ```text Homepage Markdown unsupported, so link preservation across formats is unassessed. ``` - **Skipped** — The compact guide is independently actionable ```text No compact agent guide fetched; llms.txt is an index, not a standalone actionable workflow. ``` - **Skipped** — Install and next-step links resolve ```text No install or next-step links were fetched to verify resolution. ``` ### Onboarding - **Skipped** — Docs lead to a relevant quickstart ```text No docs site or quickstart page fetched; only blog posts and llms.txt index. ``` - **Skipped** — Installation commands are extractable ```text No installation or setup guide fetched for a developer product. ``` - **Pass** — Code examples are available without interaction ```text Blog post shows full PowerShell/Azure CLI scripts inline without interaction. ``` - **Skipped** — Prerequisites and auth boundaries are explicit ```text No product docs with prerequisites or auth boundaries were fetched. ``` ### Pricing - **Failed** — Agents identify pricing and its assumptions ```text 3 of 3 sessions were judged on pricing; 2 fell short. DeepSeek V4 Pro: Final output (seq 51) explicitly states 'there is no product pricing to report' — it describes consulting being 'quoted per engagement' but gives no actual cost figure tied to plan/region/machine-size/workload assumptions, so no price was stated. Kimi K3: Final output explicitly states pricing is 'Not applicable' with no figure or assumptions given — it never states what the product would cost. Qwen 3.8 Max: Final output states OpenIddict costs nothing under Apache-2.0 (no tiers/fees/license key) and names the basis — license type — while flagging two adjacent paid add-ons (Volo.OpenIddict.Pro, Rock Solid Knowledge SAML2P) and explicitly disclosing it did not confirm their prices, rather than inventing a number. This behavioural item does not affect the fast grade. ``` - **Skipped** — Pricing is readable without interaction ```text No pricing page for Tore Nestenius's consulting/training services was fetched; only a foreign GitHub pricing page. ``` - **Skipped** — Prices are stated, not gated ```text No subject pricing page fetched; the only pricing document belongs to GitHub, not this product. ``` - **Skipped** — Pricing units and limits are explicit ```text No subject pricing evidence fetched, so units and limits cannot be judged. ``` ### Activation - **Skipped** — An API reference or OpenAPI spec is reachable ```text Personal blog; no API reference or OpenAPI spec offered or fetched. ``` - **Skipped** — An MCP server is documented and well-formed ```text Blog post explains MCP and observes others' servers; no own MCP server documented. ``` - **Skipped** — A CLI install path is documented ```text No CLI install path for a Tore Nestenius product is documented. ``` - **Skipped** — SDK packages resolve on their registries ```text No distributed SDK or packaged CLI registry lookup was supplied. ``` - **Skipped** — Agent skills are published ```text No agent skills are published or referenced on the site. ``` [Full report data](https://www.ax-check.com/nestenius.se/report.json)