~/talks

Guillaume Laforge

what they talk about

all 19 in the filters

where they keep going back

all 26 in the filters

on a stage with

all 24 in the filters

who talks about the same things

titleconferencedate
Choose your own adventure in agentic design patternsJNation 20262026-05-26
Shows concrete patterns and runnable examples: a Deep Research pipeline wired to the Gemini interactions API that chains topic-explorer → Deep Research agent →…
Talk on
Panel Software Engineering in the age of AIJNation 20262026-05-26
A live panel surveys agent tooling and real projects: hands‑on use of LangChain4J and ADK for Java, greenfield work produces usable code quickly while legacy…
Talk on
Standards and AI Agents: an Overview of MCP, A2A, ADK and MoreDevoxx France 20262026-04-22
Overview of IA agent standards and frameworks: explains protocols MCP, A2A, ACP and frameworks ADK, Arc, Quarkus, LangChain4j. Shows how to build an agent…
Talk in French on
Agentic Design Patterns Where You Are the HeroDevoxx France 20262026-04-22
Guillaume Laforge (Google) presents concrete agent design patterns for building multi-agent systems using Java tooling (LangChain4j, ADK for Java). He explains…
Talk in French on
Les Cast Codeurs 2026: No Headsets, No Screens, Just JoyDevoxx France 20262026-04-22
A live in-person wrap-up session for Devoxx France 2026 where the Cast Codeurs hosts (Arnaud Héritier, Guillaume Laforge, Emmanuel Bernard, Antonio Goncalves)…
Talk in French on
Under the Hood of LLMs — all those questions you never dared ask about themDevFest Toulouse 20252025-11-13
Describes why large language models are trained on enormous corpora (about 13 trillion tokens) and why they use subword tokenization rather than characters or…
Talk in French on
Intelligent Agents, the New Frontier of LLMsDevFest Nantes 20252025-10-16
Defines what makes a system an “agent” versus a plain LLM, outlines LLM limitations, and demonstrates building concrete agents in Java using LangChain4j and…
Talk in French on
Things you never dared to ask about LLMsVoxxed Days Zürich 20252025-03-25
Explains why LLMs work on tokens not letters, citing tokenizers like BPE and sentencepiece tokenizer, vocabulary sizes (Gemini ~260,000 tokens, GPT‑4 ~128k)…
Talk on
RAG: from dumb implementation to serious resultsJfokus 20252025-02-03
Shows concrete fixes and code using LangChain4j and Gemini/Vertex AI: embedding sentences but returning paragraph context with a sliding-window sentence…
Talk on
Gemini, Google's Large Language ModelDevFest Toulouse 20242024-11-07
Introduction to Google/DeepMind’s Gemini family of LLMs (Nano to Ultra and the open Gemma variant) and how to use Gemini via the Google Cloud API in Java apps…
Talk in French on
Panel Discussion: LangChain4j, a year later.Devoxx Belgium 20242024-10-07
LangChain4j now has over 150 contributors and ships concrete features: Gemini multimodal support with a 2 million token context and PDF/audio/video handling…
Talk on
RAG: from dumb implementation to serious resultsDevoxx Belgium 20242024-10-07
Practical RAG with LangChain4j and Gemini shows concrete fixes: implement sliding-window and recursive chunking, generate hypothetical questions or contextual…
Talk on
From naive to advanced RAG: the complete guideDevoxx Belgium 20242024-10-07
Shows a concrete RAG pipeline built with LangChain4j and production deployments on Astra/Cassandra using a G‑Vector index; demonstrates specific fixes…
Talk on
Gemini, Google's Large Language ModelVoxxed Days Brussels 20242024-05-21
Gemini is a multimodal LLM with sizes Nano, Pro, Ultra and a Flash flavor that streams responses fast and supports a 1 million token context (examples: one…
Talk on
Gemini, Google's Large Language ModelGeeCON 20242024-05-15
Gemini is natively multimodal and ships as Nano, Pro and Ultra with a new Gemini 15 Flash variant that aims for faster, cheaper responses. It accepts up to a 1…
Talk on
Generative AI in Practice: Concrete LLM Use Cases in Java with the PaLM APIJCON WORLD ONLINE 20232023-11-20
Shows how Java calls Google Cloud’s PaLM API (the model trained on ~3.6 trillion tokens, with examples mentioning ~340B parameters) to do real tasks: a…
Talk on
Generative AI in Practice: Concrete Use Cases for an LLM in JavaDevFest Toulouse 20232023-11-16
Shows how to use Large Language Models from Java without Python, using Google's PaLM models via the Vertex AI API. Demonstrates practical Java examples for…
Talk in French on
Skyrocketing Micronaut microservices into Google CloudCloud Builders: Java Conf 20232023-03-30
Shows how to deploy Micronaut apps as functions, apps or containers using Micronaut Launch templates and direct GitHub pushes; demos include a Pub/Sub…
Talk on
Monitoring Your 3D Prints with an Old Smartphone, from WebRTC…BDX I/O 20222022-12-02
A developer repurposed an old smartphone as a webcam to monitor 3D prints remotely and avoid walking up and down stairs. The setup streams video using WebRTC…
Talk in French on
Choreography vs Orchestration in serverless microservicescode.talks 20222022-09-15
Compares three concrete patterns and shows working demos: Google Cloud Workflows orchestrates Cloud Run, Cloud Functions and external APIs (SendGrid via Secret…
Talk on
Choreography vs Orchestration in Serverless MicroservicesVoxxed Days Luxembourg 20222022-06-21
Compares orchestration (a central coordinator controlling interactions) versus choreography (services working independently and communicating via events) for…
Talk in French on
Asynchronous operations in UI using Workflows and FirestoreGoogle I/O 20222022-05-11
Client JavaScript calls a Cloud Function that uses the Workflows Executions API to start an execution which orchestrates services (payments, Document AI…
Talk on
Adding a search bar to your application from A to ZDevoxx France 20222022-04-20
Shows how to add a search bar to a photo-sharing application by indexing image metadata stored in Google Cloud Firestore and enabling rich searches beyond…
Talk in French on
Choreography vs Orchestration in serverless microservicesNDC Oslo 20212021-11-29
Compares Pub/Sub event choreography versus centralized Cloud Workflows orchestration by rebuilding a photo‑sharing app: original pipeline uses Cloud Storage…
Talk on
Choreography vs Orchestration in serverless microservicesJCON-ONLINE 20212021-10-05
Photo-sharing app moves from messy event-driven wiring (Pub/Sub/Eventarc plus Cloud Functions, Cloud Run, Firestore, Vision API) to a central orchestrator…
Talk on
The Cast Codeurs at Devoxx France 2021: we wanted to see people againDevoxx France 20212021-09-29
A live recording of the French podcast Les Cast Codeurs during Devoxx France 2021, featuring Emmanuel Bernard, Antonio Goncalves, Arnaud Héritier, Guillaume…
Talk in French on
Artificial intelligence to the rescue of accessibilityDevoxx France 20212021-09-29
Demonstrates using Google Cloud tools to improve accessibility: Video Intelligence extracts scene labels and timestamps, Speech-to-Text transcribes audio in…
Talk in French on
Choreography vs Orchestration in serverless microservicesDevoxx France 20212021-09-29
Compares event-driven choreography with a central orchestrator by reimplementing a photo‑sharing demo: the original Pub/Sub + Cloud Functions + Cloud Storage +…
Talk in French on
What's next for the Groovy web console?ApacheCon@Home 20212021-09-21
A redesigned Groovy web console v2 runs on Google Cloud with static front end on App Engine and a pool of Cloud Functions per Groovy version (Java 11)…
Talk on
Implementing a Webhook, Not So Simple!DevFest du Bout du Monde 20202020-02-28
An introduction to Webhooks followed by hands-on work: first implementing a callback endpoint to receive event notifications, then building a server-side…
Talk in French on
Implementing a server-side webhook, not so simple!BDX I/O 20192019-11-15
The talk explains how to implement server-side webhooks: it first introduces webhooks and building a callback endpoint to receive notifications, then covers…
Talk in French on
Cloud Run, serverless containers in actionVoxxed Days Microservices 20192019-10-21
Cloud Run deploys containers to production in seconds, runs managed on Google Cloud or on GKE via Knative, and scales 1 to 0 with billing per 100ms and a…
Talk on
Implementing a server-side webhook, not so simpleOrléans Tech Conf 20192019-09-17
Explains webhooks from both sides: after a brief concept intro it shows how to implement a server callback to receive events and then how to implement a…
Talk in French on
What's new in Google Cloud serverlessDevFest du bout du monde 20192019-02-22
A concrete photo‑sharing app built using App Engine, Cloud Functions, Google Cloud Storage and Cloud Datastore that auto‑labels images with Cloud Vision and…
Talk in French on
What's new in Google Cloud ServerlessDevFest Paris 20192019-02-08
A demo of a serverless image‑sharing app using Google Cloud: a Java App Engine frontend, a Go admin module, photos in Cloud Storage, metadata in Datastore…
Talk in French on
Machine Learning APIs, from Training [...]DevFest Toulouse 20182018-11-08
Shows concrete demos of Google Cloud Machine Learning APIs: Vision API for label, adult-content and dominant-color detection from images; Speech-to-Text…
Talk in French on
New serverless solutions on Google Cloud for functions, apps and containersVoxxed Days Microservices 20182018-10-29
New Google Cloud serverless features include Cloud Functions GA with Node.js and Python 3.7, modern App Engine runtimes running in a gVisor sandbox, and the…
Talk on
Google Cloud's new serverless featuresDevFest Nantes 20182018-10-18
A live demo builds a photo‑sharing backend that uploads images with App Engine (Java), stores blobs in Cloud Storage, uses the Vision API to analyze images…
Talk in French on
Chatbots, shall we shift into second gear?Devfest Lille 20182018-06-21
Explains building chatbots using Dialogflow for intent and entity extraction, extending them with Actions on Google, and implementing account linking for…
Talk in French on
Get silly with serverlessDevoxx Belgium 20172017-11-06
Shows how Google Cloud Functions (Node.js) glue services: upload an image to Cloud Storage, a function invokes Cloud Vision for labels and creates a thumbnail…
Talk on
Ok Google, is there any presentation about ChatBotsDevFest Nantes 20172017-10-19
Demonstrates building a voice-enabled chatbot/assistant that can answer conference-related queries (e.g., find sessions on Machine Learning or Docker, look up…
Talk in French on
IT Holy WarsVoxxed Days Singapore 20172017-06-02
A brisk survey of developer polarizations that names concrete tradeoffs and tools: tabs versus spaces, VI versus Emacs, Gradle versus Maven. Covers dynamic vs…
Talk on
Machine Intelligence at Google ScaleVoxxed Days Singapore 20172017-06-02
Overview of available Google Cloud ML tools and concrete outcomes: ready-made APIs like Cloud Vision API, Speech, Natural Language, Translate (now neural MT)…
Talk on
What can you learn from thousands of source files in Github?Devoxx US 20172017-03-21
Uses GitHub’s BigQuery dataset (3 TB, ~2.8M repos, 145M commits, 163M latest-file revisions) and SQL queries with regex-extract and quantiles to analyze…
Talk on
Cloud Native EnterpriseSpringOne2GX 20152015-09-14
Recorded at SpringOne2GX 2015. Speakers: Guillaume LaForge, Graeme Rocher, Josh Long, Dr. David Syer, Mark Fisher, Scott Frederick Slides…
Talk
Groovy, in the light of Java 8SpringOne2GX 20142014-09-08
Groovy claims that Java 8 is complementary, not redundant: Groovy closures coerce to functional interfaces (and even abstract classes) so existing code can…
Talk on
~/search
type to search 6,249 conferences, 138,987 speakers and 185,172 talks
~/help
cmdctrl k
search every conference, speaker and series
/
focus the filter search
h
home
c
conferences
s
speakers
e
series
t
light / dark — the status bar button does the same
?
this help
esc
close this, then clear every filter — or just the search, while you are typing in it

Ignored while you are typing. Pages without a filter rail have no search to focus.