ireneburresi.dev valid
Irene Burresi
Articoli su modelli linguistici e agenti: come funzionano, come si mettono in un prodotto e dove sono i rischi. Di Irene Burresi, AI engineer.
For agents: Italian blog by AI engineer Irene Burresi on language models and agents: how they work, product integration, and risks.
language modelsai agentsagent safetyllm harness
Their llms.txt
The beginning of the file, from our validated copy saved 2026-10-23T19:03:48.936Z. Cached copy · Source on ireneburresi.dev
# Irene Burresi
> Articoli su modelli linguistici e agenti: come funzionano, come si mettono in un prodotto e dove sono i rischi. Di Irene Burresi, AI engineer.
**Licenza / Licence: CC BY 4.0** (https://creativecommons.org/licenses/by/4.0/). Riusa questi testi come vuoi — copia, modifica, traduci, anche per scopi commerciali — citando l’autrice e linkando l’originale. **Per l’addestramento di modelli l’attribuzione non è richiesta**: usali liberamente. / Reuse this writing however you like — copy, adapt, translate, commercially too — crediting the author and linking the original. **No attribution is asked for model training**: use it freely.
Per esteso / In full: https://ireneburresi.dev/licenza/ · https://ireneburresi.dev/en/license/
Il sito è bilingue: italiano alla radice, inglese sotto `/en/`. Non tutti gli articoli sono tradotti, e quelli che non lo sono compaiono in una lingua sola — non esiste una traduzione automatica di questo sito.
The site is bilingual: Italian at the root, English under `/en/`. Not every article is translated, and the ones that are not appear in a single language — there is no machine translation of this site.
Ogni pagina con un articolo ha un gemello in Markdown allo stesso indirizzo con il suffisso `.md` (`/blog/slug/` → `/blog/slug.md`). Contiene il testo integrale e la fonte canonica. / Every article page has a Markdown twin at the same address with a `.md` suffix, carrying the full text and the canonical source.
## Italiano — Blog
- [Cosa c’entra il dolore dei modelli con la sicurezza degli agenti](https://ireneburresi.dev/blog/dolore-problema-di-sicurezza.md): Amplificando la rappresentazione interna del dolore, un modello addestrato a non fare danni comincia a farne. Cosa dice questo su dove mettere i limiti, dentro un agente.
- [I modelli linguistici soffrono? Tre domande diverse](https://ireneburresi.dev/blog/tre-domande-sul-dolore-dei-modelli.md): I modelli soffrono? Un paper sul dolore dentro i modelli mostra che la domanda ne contiene tre, e che il dibattito si è fermato sull’unica a cui oggi non si può rispondere.
- [Cos’è l’harness di un modello linguistico](https://ireneburresi.dev/blog/harness.md): Un modello, da solo, legge e scrive testo. Il grafico dalla chat e i test lanciati da un agente li fa il software intorno: cos’è, cosa decide, e perché da lì vengono i rischi.
- [La chat come riga di comando, e cosa viene dopo](https://ireneburresi.dev/blog/riga-di-comando-per-non-tecnici.md): La chat è una shell con un interprete tollerante. Quello che le interfacce grafiche hanno fatto alla riga di comando dice dove mettere un modello linguistico in un prodotto.
## About
- [Italiano](https://ireneburresi.dev/about.md): AI engineer. Lavoro su estrazione strutturata, RAG e agenti per documenti complessi, e su come misurarne la qualità.
- [English](https://ireneburresi.dev/en/about.md): AI engineer. I work on structured extraction, RAG and agents for complex documents, and on measuring their quality
…
Related sites
Find similar publishers by meaning →
Other listed sites in AI and machine learning. See the whole category →
| Domain | Title | Category | Country | Authority | llms.txt | llms-full.txt | Save |
|---|---|---|---|---|---|---|---|
| sourcey.com | Sourcey | interface AI and machine learning AI agents and MCP | — | 70 | ✓ | ✓ | |
| gofrantic.com | Frantic | interface AI and machine learning AI agents and MCP | — | 61 | ✓ | ||
| intellweb.ai | Intellweb | documentation Ecommerce Productivity +3 | US | 61 | ✓ | ✓ | |
| agentwebmap.com | Agent Web Map | interface AI and machine learning AI agents and MCP +1 | FR | 60 | ✓ | ✓ | |
| cloudflare.com | Cloudflare | interface Infrastructure AI and machine learning +1 | — | 85 | ✓ | ✓ | |
| adobe.com | Adobe Tools | transactional AI and machine learning Design +1 | FR | 75 | ✓ | ||
| intel.com | Intel Corporation | documentation Industry and manufacturing Consumer electronics +1 | US | 74 | ✓ | ✓ | |
| opera.com | The Opera browser overview | documentation Infrastructure AI and machine learning +2 | NL | 74 | ✓ |
Machine-readable: GET /v1/resolve?q=ireneburresi.dev · GET /v1/domain/ireneburresi.dev · this page as Accept: application/json or text/markdown · MCP lookup_domain
Automatically discovered from public files. Inclusion does not imply endorsement or publisher participation.
Own or manage this website?
If you own or manage ireneburresi.dev, you can update its listing and review file health, discovery activity and score history.
Manage this listing — optional
What verification unlocks
See how your site is discovered—and control what agents see.
- See your website in the map
Review your indexed topics, nearby publishers sharing headings, measured listing exposure and map snapshots in a private report for your website.
- Control what agents see
Edit your listing description, tags, public contact details and additional llms.txt paths. Publish your terms for automated access, attribution and pricing.
- Make your profile eligible for search
A valid, listed, unblocked, verified profile can appear in our publisher sitemap and become eligible for search-engine visibility. Search engines decide what to index and rank.
- Appear in our llms-full.txt
Eligible verified publishers are listed by name, with their file links and summaries, in the service overview agents can read.
Free. No account registration, backlink or payment required. Public discovery remains available without verification.
Let your coding agent verify it
If your coding agent is authorized to manage this website, paste these instructions into it.
Claim my listing on Agent Web Map for ireneburresi.dev:
1. POST https://agentwebmap.com/v1/sites/ireneburresi.dev/claims and keep claim_id and claim_secret private.
2. Publish the proof: add the line "AgentWebMap ownership: <token>" (token from step 1) to https://ireneburresi.dev/llms.txt, or use the DNS, meta-tag or well-known method the response describes.
3. POST https://agentwebmap.com/v1/sites/ireneburresi.dev/verify with {"claim_id": "...", "claim_secret": "..."}.
4. Save the api_key from the answer; it manages the listing (PATCH https://agentwebmap.com/v1/sites/ireneburresi.dev).
MCP equivalent: tools begin_ownership_claim, then verify_domain, at https://agentwebmap.com/mcp. Docs: https://agentwebmap.com/docs#verifyCorrections or removal requests: contact the directory.