Ask Hans: PromptQuorum in plain words
Ask Hans is the AI assistant of PromptQuorum. Tell it what you want to do and which computer you have. It looks up the app directory, guides and hands-on tests with the same tools the PromptQuorum MCP server offers, then recommends apps, compares them and checks them against your hardware.
- Recommends one app and says why, instead of listing ten.
- Links every claim to the review, test or directory entry it comes from.
- Shows a confidence tag per app: tested by PromptQuorum, checked by the maker, or maker statements only.
- 218
- Questions answered
- 127
- Times opened
Counted since November 1, 2026. Anonymous totals for all visitors: no names, no IP addresses, no question text.
How Ask Hans works
You write a question in your own words, in any language. Ask Hans decides which PromptQuorum tools to call, reads the results and answers in your language, with links to the pages it used. It only uses content from promptquorum.com.
The four steps
- 1You ask
- 2Ask Hans calls tools
- 3You get an answer with sources
- 4Matching links and follow-up questions appear
What Ask Hans can look up
Ask Hans uses the same tools as the public PromptQuorum MCP server, called directly on our server. Each card shows one tool and a question that makes Ask Hans use it.
See the MCP server pageFind apps
- find_best_appsFind the best apps for you
Turns a plain-language goal plus your operating system and memory into a ranked shortlist, with reasons and honest trade-offs.
Ask:
I have a 24 GB Mac and want to chat with my PDFs without using the terminal.
- search_appsRecommend apps
Recommend local-AI apps from the directory that match a stated goal and hardware.
Ask:
Free Windows apps for image generation that run on 8 GB of VRAM.
- recommend_stackRecommend an app stack
Suggests a ready-made combination of apps for a goal, such as Ollama + Open WebUI, together with its hardware floor.
Ask:
Which apps should I combine for a private coding assistant with 32 GB of RAM?
- find_local_alternativeFind a local alternative
Maps a cloud AI product such as Midjourney or ElevenLabs to local alternatives, and states the gaps honestly.
Ask:
What is a local alternative to ElevenLabs?
- get_app_alternativesFind app alternatives
Finds similar apps when one is too hard, too costly or does not fit your machine.
Ask:
ComfyUI is too complicated for me — what is easier?
- get_app_detailsGet directory entry
Fetch license, hardware requirements, platforms, price and URL for one tool.
Ask:
What are the license and hardware needs of Ollama?
- list_categoriesList categories
List directory categories, use cases and operating systems.
Ask:
Which app categories exist, and how many apps are in each?
Decide and check
- compare_appsCompare apps
Compare local-AI apps side by side on license, hardware, platforms and price.
Ask:
Compare Ollama, LM Studio and Jan for a beginner.
- check_hardware_compatibilityCheck hardware compatibility
Says whether an app — and optionally a specific model size — fits your platform and memory, and what to try instead if it does not.
Ask:
Will ComfyUI run on my Windows laptop with 8 GB of VRAM?
- estimate_vramEstimate VRAM
Estimates the memory a model needs from its size, quantization and context length, and whether it fits what you have.
Ask:
How much memory does a 32B model need at Q4 with an 8K context?
- explain_licenseExplain a license
Explain the core rule of a software license (AGPL-3.0, Apache 2.0, MIT, …) in plain language.
Ask:
Can I use an AGPL-3.0 app inside my company's product?
Read and learn
- search_promptquorumSearch PromptQuorum
Search local-LLM guides, prompt-engineering articles, and the software directory.
Ask:
How do I run Llama on a Mac?
- get_articleGet PromptQuorum article
Fetch the full content of one article by cluster and slug.
Ask:
Open the full guide you just found.
- get_pageRead a page
Returns the readable text of one page from list_pages, for example the home page, About, Security or Privacy. Use it when a question is about the site itself rather than an article.
Ask:
What does the PromptQuorum About page say?
- list_pagesList readable pages
Lists every page of the site that is not an article, such as the home page, About, the PromptQuorum app page, Security and Privacy, with a short description of each.
Ask:
Which pages does PromptQuorum have besides the articles?
- find_related_contentFind related content
Collects the review, comparison guide, hands-on test and setup articles for an app or topic.
Ask:
Show me the review and setup guides for Open WebUI.
- get_hands_on_testHands-on test findings
Returns PromptQuorum's own hands-on findings for an app, with evidence labels — or says plainly that it was not tested.
Ask:
Did PromptQuorum actually test BoBe, and what went wrong?
- get_latestWhat's new
Lists recently added apps, updated articles and published hands-on tests, newest first.
Ask:
What was added to the directory recently?
- list_clustersList content clusters
List every content section on the site with a short description.
Ask:
What topics does PromptQuorum cover?
Power Mode: five guided reports
Power Mode turns Ask Hans from a chat into a guided process. Switch it on with the Power Mode switch in the Ask Hans window, the Power Mode card on the welcome screen or the card in the search window. You answer a few fixed questions, then Ask Hans writes one complete report.
- maxMAX – Full Setup
Describe your computer and your goals. Get the software to install, what is easy and what is at the limit.
Typical time: 5–8 min
- auditAudit My AI Setup
Tell us what you use today. Get an honest assessment, five ranked improvements and a roadmap, with cloud AI kept where it is the better tool.
Typical time: 5–8 min
- hardwareHardware Selector
What to keep, upgrade or buy for local AI within your budget.
Typical time: 4–6 min
- solutionSolution Setup
Pick a goal such as video or voice and get a setup matched to your hardware.
Typical time: 4–6 min
- mobileMobile Apps
Find on-device AI apps that fit your phone's memory and storage.
Typical time: 2–3 min
Each report lists your inputs, the recommended software with reasons, what runs easily and what is at the limit, and links to the PromptQuorum pages it used. Memory fits are estimates that PromptQuorum calculates from its own data (rule-of-thumb figures, not measurements); an AI writes the text around them with the same PromptQuorum tools as the chat. Check prices, versions and compatibility on the linked pages before you buy or install anything.
Limit: 6 reports per visitor per 24 hours. Writing one report can take up to two minutes.
A worked example
I have a Mac with 24 GB of memory. What should I use to chat with my PDFs?
Tool used: recommend_stack
For chatting with PDFs, the directory suggests Ollama, which runs the model, together with AnythingLLM, which lets you load your PDFs and ask questions about them. The stack needs about 16 GB of RAM, with a GPU optional, so your 24 GB is enough. Both are free and run on a Mac. The directory has no verified memory figure for each app, so treat 16 GB as a guideline for the whole stack, not a guarantee.
Links the assistant gave
The same question and tool as on the MCP page. Ask Hans answers a little shorter, adds a confidence label to each app and suggests follow-up questions. Answers differ from case to case.
How to read the answers
- 1Ask Hans is an AI, not Hans himself, and it can be wrong. Check important facts on the linked pages.
- 2Every app carries a confidence label. High: PromptQuorum tested it hands-on. Medium: the maker checked the entry, we did not test it. Low: only maker statements and directory data, so check the maker's page.
- 3It answers from promptquorum.com only: no web search, no news, no live prices. If it finds nothing, it says so.
- 4There is a limit of 50 questions per visit and 500 characters per question.
- 5Your question is sent to our server and to Anthropic (Claude) to create the answer. Please do not enter personal data. Conversations stay in your browser and are kept for 7 days only if you choose to save them.
- 6Power Mode sends your answers to its questions (hardware, goals, optional note) to our server and to Anthropic (Claude) to write the report. Please do not put personal data in the note field.
What it does not do
No legal, medical, financial or electrical-installation advice: ask a qualified professional. It does not install, change or buy anything for you.
Ask Hans usage
Totals count every visitor; the breakdowns count only visitors who agreed to anonymous statistics. Never stored: names, IP addresses, question text.
| Ask Hans usage | Today (UTC) | Yesterday | Last 7 days | Last 30 days | All time |
|---|---|---|---|---|---|
| Questions answered | 10 | 17 | 206 | 218 | 218 |
| Times opened | 3 | 17 | 119 | 127 | 127 |
| Power Mode reports | 0 | 4 | 4 | 4 | 4 |
Questions with statistics consent: 175 / 206 (Last 30 days)
Ratings
| Ratings | Today (UTC) | Yesterday | Last 7 days | Last 30 days | All time |
|---|---|---|---|---|---|
| People who rated | 0 | 1 | 4 | 6 | 6 |
| Average stars (of 5) | – | 1.0 | 2.0 | 3.0 | 3.0 |
| Rated 1 to 3 stars | 0 | 1 | 3 | 3 | 3 |
| Of those, started an email to me | 0 | 0 | 0 | 0 | 0 |
Anonymous: one star click counts once, no names, no IP addresses, no question text. "Started an email" counts clicks on the write-email button in the pop-up; it cannot see whether the email was sent.
Use of Ask Hans
| Use of Ask Hans | Today (UTC) | Yesterday | Last 7 days | Last 30 days |
|---|---|---|---|---|
| Uses | 14 | 18 | 41 | 41 |
| Return visits | 8 | 5 | 14 | 14 |
| Share of return visits | 57 % | 28 % | 34 % | 34 % |
| Average time per use | 3:40 | 1:55 | 2:44 | 2:44 |
| Share card shown | 3 | 4 | 11 | 11 |
| Time in Ask Hans per use: under 30 seconds | 7 | 8 | 20 | 20 |
| Time in Ask Hans per use: 30 seconds to 2 minutes | 2 | 4 | 7 | 7 |
| Time in Ask Hans per use: 2 to 5 minutes | 2 | 5 | 8 | 8 |
| Time in Ask Hans per use: 5 to 15 minutes | 2 | 1 | 5 | 5 |
| Time in Ask Hans per use: over 15 minutes | 1 | 0 | 1 | 1 |
Counted only for visitors who chose "Yes, I agree". A use ends when the Ask Hans window is closed or the page is left. Only active time counts (window open, tab visible). A return visit is a visit in a later browser session on the same device. Times are shown in ranges; the average is an estimate from those ranges.
Power Mode reports by process
| Power Mode reports by process | Today (UTC) | Yesterday | Last 7 days | Last 30 days |
|---|---|---|---|---|
| Solution Setup | 0 | 2 | 2 | 2 |
| Audit My AI Setup | 0 | 1 | 1 | 1 |
| Hardware Selector | 0 | 1 | 1 | 1 |
Report copies and downloads
| Report copies and downloads | Today (UTC) | Yesterday | Last 7 days | Last 30 days |
|---|---|---|---|---|
| 0 | 4 | 4 | 4 | |
| Word | 0 | 1 | 1 | 1 |
| Markdown | 0 | 1 | 1 | 1 |
Reports are counted for all visitors, when the report is finished. Copies and downloads are counted only for visitors who agreed to the anonymous statistics, by format; PromptQuorum does not store the report text.
What people ask about
| What people ask about | Today (UTC) | Yesterday | Last 7 days | Last 30 days |
|---|---|---|---|---|
| General (fallback) | 2 | 5 | 55 | 55 |
| Local LLMs | 4 | 5 | 45 | 45 |
| Find an app | 1 | 0 | 18 | 18 |
| Image generation | 0 | 5 | 16 | 16 |
| GPUs and VRAM | 0 | 1 | 10 | 10 |
| Code assistants | 0 | 0 | 6 | 6 |
| Inference engines | 2 | 0 | 6 | 6 |
| PromptQuorum apps | 0 | 0 | 6 | 6 |
| Prompt Engineering | 0 | 0 | 5 | 5 |
| Agent frameworks | 0 | 0 | 3 | 3 |
| Chat clients | 1 | 0 | 3 | 3 |
| Document and PDF chat | 0 | 0 | 1 | 1 |
Tools Ask Hans used
| Tools Ask Hans used | Today (UTC) | Yesterday | Last 7 days | Last 30 days |
|---|---|---|---|---|
| search_promptquorum | 2 | 6 | 67 | 67 |
| find_best_apps | 2 | 3 | 29 | 29 |
| search_apps | 2 | 0 | 25 | 25 |
| get_article | 0 | 0 | 19 | 19 |
| estimate_vram | 0 | 1 | 13 | 13 |
| find_related_content | 0 | 2 | 7 | 7 |
| compare_apps | 2 | 1 | 6 | 6 |
| get_app_details | 0 | 3 | 6 | 6 |
| list_clusters | 0 | 0 | 4 | 4 |
| list_categories | 0 | 0 | 3 | 3 |
| get_hands_on_test | 0 | 0 | 2 | 2 |
| check_hardware_compatibility | 0 | 0 | 1 | 1 |
Apps researched
| Apps researched | Today (UTC) | Yesterday | Last 7 days | Last 30 days |
|---|---|---|---|---|
| Ollama | 3 | 0 | 8 | 8 |
| GPT4All | 1 | 0 | 5 | 5 |
| Immich | 0 | 0 | 4 | 4 |
| LM Studio | 2 | 0 | 4 | 4 |
| Jan | 1 | 0 | 3 | 3 |
| Locally Uncensored | 0 | 2 | 3 | 3 |
| AnimateDiff | 0 | 1 | 2 | 2 |
| Llamatik | 0 | 0 | 2 | 2 |
| LobeHub | 0 | 0 | 2 | 2 |
| oMLX | 0 | 0 | 2 | 2 |
| Atomic Bot | 0 | 0 | 1 | 1 |
| AUTOMATIC1111 | 0 | 0 | 1 | 1 |
Directory categories researched
| Directory categories researched | Today (UTC) | Yesterday | Last 7 days | Last 30 days |
|---|---|---|---|---|
| General chat clients | 1 | 1 | 16 | 16 |
| Photo libraries & search | 0 | 0 | 4 | 4 |
| Image generation | 0 | 0 | 3 | 3 |
| Inference engines | 1 | 0 | 3 | 3 |
| Notes & knowledge bases | 1 | 0 | 2 | 2 |
| Runtimes & model managers | 0 | 0 | 2 | 2 |
| Speech-to-text | 0 | 0 | 2 | 2 |
| Video generation | 0 | 0 | 2 | 2 |
| Workflow & node builders | 0 | 0 | 2 | 2 |
| Agent frameworks | 0 | 0 | 1 | 1 |
| AI code editors | 0 | 0 | 1 | 1 |
| Code assistants & IDE plugins | 0 | 0 | 1 | 1 |
Question languages
| Question languages | Today (UTC) | Yesterday | Last 7 days | Last 30 days |
|---|---|---|---|---|
| EN | 5 | 3 | 84 | 84 |
| ZH | 0 | 0 | 21 | 21 |
| ES | 0 | 0 | 19 | 19 |
| DE | 1 | 12 | 18 | 18 |
| KO | 3 | 0 | 11 | 11 |
| AR | 0 | 0 | 8 | 8 |
| FR | 0 | 1 | 6 | 6 |
| JA | 1 | 0 | 6 | 6 |
| PT | 0 | 0 | 2 | 2 |
The topic is one label per question. Tools, apps and categories show what Ask Hans looked up, so one question can appear in several rows and the tables do not add up to the number of questions. The tables start on the day counting began.