Artificial Intelligence | Giulia Solinas

Building Agents in Bob with a Software Spec Driven Approach

Fri, 03 Jul 2026 00:00:00 +0000

Building Agents in Bob with a Software Spec Driven Approach

Agentic systems become easier to build, review, and evolve when they are treated like software products instead of clever prompts. Bob’s dedicated skills support exactly that style of work: start with business intent, turn it into explicit specifications, generate implementation artifacts, and then analyze the result against the design.

In this post, I describe how to use Bob and four dedicated skills as an end-to-end, spec driven workflow for creating watsonx Orchestrate (wxO) agentic solutions.

Why Spec Driven Agent Development Matters

Traditional agent building often starts with a prompt and quickly jumps into tools, flows, and integrations. That can work for experiments, but it becomes fragile when the solution has real business logic, compliance expectations, system integrations, or multiple collaborators.

A software spec driven approach flips the sequence:

Define the business problem before choosing the implementation.
Produce architecture and process specifications before generating code.
Keep business rules legible in Standard Operating Procedures (SOPs).
Generate wxO artifacts from the agreed specification.
Analyze the implementation and feed findings back into the next iteration.

In this framework, the specification is not a bulk of documentation that none reads and gets under the deck of work to be done for a client. It is the contract that the developer signs with the agent.

The Bob Skill Pipeline

We can bring into the Bob’s workspace (global or at the project level) four specialized skills that form a complete pipeline for designing, building, and auditing wxO agentic solutions:

Skill	Primary Question	Output
`solution-architect`	What should we build, and why?	Solution overview, architecture, and implementation plan
`sop-builder`	How should the business process work?	Structured SOP with process flow, data needs, rules, and decisions
`wxo-builder`	How do we turn the spec into wxO artifacts?	Importable wxO project with agents, tools, flows, connections, and scripts
`wxo-analyzer`	Does the implementation match expectations?	Documentation and audit reports for an existing wxO project

The skills are avaialble in the GitHub repository for . We can clone the repo and import the folders into our project.

The important pattern is that each skill produces the input for the next one. That makes the workflow traceable from business problem to deployed solution.

Step 1: Start with `solution-architect`

Use solution-architect when you have a business problem or use case, but no technical design yet.

Example prompt:

I need an AI agent that processes invoices from a shared mailbox, extracts invoice data, validates it against vendor records, and prepares a SalesForce update.

The goal at this stage is not to write code. The goal is to create a shared understanding of the solution.

The agent using the solution-architect skills should produce three key documents:

Document	Purpose
Solution Overview	Captures the executive summary, business context, problem statement, and agent requirements
Solution Architecture	Describes components, integrations, data flow, security, and architecture diagrams
Implementation Plan	Breaks the work into phases, assumptions, constraints, and SOP candidates

The implementation plan is especially important because it decomposes the solution into business processes that can be specified independently.

Step 2: Convert Architecture into SOPs with `sop-builder` skills

Use sop-builder skills when you have an architecture document, workflow description, BPMN model, Langflow export, n8n export, or any other process-oriented input.

This skill turns design intent into a plain-language Standard Operating Procedure. That SOP becomes the specification for implementation.

A good SOP includes:

Business process flow diagrams
Business context and problem statement
Input, processing, and output data requirements
Business rules and decision points
Integration expectations
Error handling and escalation behavior

This is where the spec driven approach becomes practical. Instead of embedding business logic directly in generated tools or agent instructions, you first make that logic visible and reviewable.

Example prompt:

Build the SOP for the invoice extraction and validation flow from the implementation plan.

For larger solutions, a good option can be creating one SOP per major flow. A single monolithic SOP usually hides important decisions and makes generation harder to review.

Step 3: Generate the wxO Solution with `wxo-builder` skills

Use Bob with wxo-builder skills when you have an SOP or a very clear build prompt and want actual watsonx Orchestrate artifacts.

This is the point where Bob moves from specification into implementation. Given a strong SOP, wxo-builder can generate an importable wxO project structure such as:

my_solution/
 agents/
 my_agent.yaml
 tools/
 my_tool.py
 my_flow.py
 connections/
 my_connection.yaml
 main_flow.py
 import-all.sh

The agent with the builder skills can create:

Native wxO agents
Python tools with correct decorator and docstring conventions
Flow Builder patterns for document processing, user activity, conditional logic, and multi-agent workflows
Knowledge base configurations
Connection YAML files for credential management
Import scripts for repeatable setup

The quality of the generated solution depends heavily on the quality of the SOP. If the SOP defines the business rules, data contracts, exception paths, and integration behavior, the builder has fewer assumptions to invent.

Example prompt:

Generate the wxO solution from this SOP. Create the agent configuration, required Python tools, connection specs, and import script.

This step should usually happen in Agent mode because it writes project files. Note that you can further empower the agent mode by giving MCP connections to the Orchestrate documentation through the wx orchestrate ADK. However, a downside of MCP connections is larger token consumptions. An alternative method would be using the CLI skills approach by Floring Manila and Niklas Heidoff as explained in this .

Step 4: Audit and Document with `wxo-analyzer` skills

Use wxo-analyzerskills when you have an existing wxO project and want to understand, document, or audit it.

The Agent with the analyzer skills should produce a three-report documentation set:

Report	Purpose
Solution Overview	Summarizes architecture, components, and file structure
Agent Analysis	Breaks down each agent, its tools, collaborators, instructions, and LLM settings
Tools and Components	Reviews flows, Python tools, connections, knowledge bases, and implementation patterns

This closes the loop. After generating or modifying a solution, analyze it and compare the reports against the original architecture and SOPs.

Useful review questions include:

Does the generated agent follow the intended process?
Are business rules represented explicitly?
Are credentials handled through connections instead of hardcoded values?
Are error paths and escalation paths implemented?
Are tools too large, too ambiguous, or missing validation?
Does the implementation introduce behavior that was not in the SOP?

The output of the step obtained with wxo-analyzer skills can feed back into the tasks for the sop-builder or wxo-builder for refinement.

A Practical End-to-End Flow

Here is the full workflow in one sequence:

Business problem
 -> solution-architect
 -> Solution overview, architecture, implementation plan
 -> sop-builder
 -> Standard Operating Procedure
 -> wxo-builder
 -> Importable wxO project
 -> wxo-analyzer
 -> Audit reports and improvement backlog

Best Practices for Spec Driven Agent Work

Start with architecture for non-trivial use cases. If the solution touches multiple systems, users, approval steps, or data sources, begin with solution-architect skills.

Keep SOPs focused. One SOP per flow makes the specification easier to review and easier for wxo-builder skills to implement cleanly.

Treat the SOP as the contract. The SOP should define data inputs, outputs, business rules, decisions, and exceptions clearly enough that implementation choices can be checked against it.

Build from reviewed specs. Do not rush from a vague idea to generated code. The fastest path is usually to clarify the spec first.

Analyze after building. Call the agent with the wxo-analyzer skills after generation or major changes so the project can be reviewed for missing error handling, hardcoded credentials, oversized flows, or behavior that drifted from the SOP.

Iterate deliberately. When the agent finds gaps, update the SOP or architecture first when the gap is conceptual. Update the wxO implementation when the spec is right but the build needs refinement.

What This Changes

Bob’s dedicated skills make agent development like professional software delivery.

The workflow creates a chain of accountability:

Business requirements explain why the agent exists.
Architecture explains how the solution should fit together.
SOPs explain how the work should happen.
wxO artifacts implement the agreed process.
Analyzer reports show what was actually built.

That chain is what makes agentic systems deliverable and maintainable. It gives teams a way to discuss requirements, review logic, generate implementation, and audit the result without losing the thread between business intent and technical behavior.

When used together, solution-architect, sop-builder, wxo-builder, and wxo-analyzer skills turn Bob into a spec driven agent factory: one that can move from idea to implementation while keeping the reasoning visible at every step.

Agentic AI

Fri, 27 Mar 2026 00:00:00 +0000

Agentic AI

Building Smarter Teams, One Agent at a Time

I specialize in designing and deploying autonomous agent ecosystems that turn complex workflows into seamless, self‑organizing teams. Using IBM watsonx Orchestrate, I assembled a sandbox crew of business analysts who collaborate in real‑time to surface users stories, automate the identification of process requirements, and accelerate decision-making.

What makes me excited about this project: high degree of specialization, modularity, possibility to scale in tasks, smaller models for each specialized agents, ReAcT capabiliites, orchestration by design.

At the same time, I explored the Google SDK for Agent Building and crafted a sandbox project—a virtual podcast crew that researches, scripts, and narrates fintech news on‑the‑fly. The agents coordinate research, fact‑checking, and voice synthesis, delivering a polished, up‑to‑date podcast episode without human intervention.

What I learned from this project: each agent is supported by a different foundation model like LLM for text creation, multi-modal models for information parsing (including imaging and IDP capabilities), and text-to-speech, each packed in diffrent agents as modular components.

Together, these experiences showcase my ability to:

Design modular agent architectures that integrate with existing data and NLP pipelines.
Orchestrate multi‑agent collaboration through clear role‑based interactions.

[NOTE!] My next chapter here in this area is AgentOps.

Do you want to co-develop with me? Just reach out.

WAID

Sun, 01 Mar 2026 00:00:00 +0000

Women in AI and Digital — From Career Change to Community

Who I Am & Why I’m Here

I didn’t start out in tech. I walked into the world of IT with an academic hat on top, an interest in stats, data, and machine learning, and a green field in front of me where I had no experience. The moment I realized I wasn’t alone, people—mentors, fellow women building AI‑driven products, and allies who believed in my potential—started pulling the missing pieces together for me. Their guidance turned my curiosity into a clear identity as an AI practitioner and leader.

Because those lifelines saved my journey, I now pay it forward. I volunteer with Women in AI and Digital (WAID), where I moderate expert interviews and mentor emerging women as they navigate their own AI pathways. Every conversation, every piece of feedback, every “aha!” moment is a reminder that the tech ecosystem thrives when we lift each other up.

What WAID Does (in a nutshell)

Women in AI and Digital was founded to unite and support women navigating the evolving worlds of AI and digital work.
Our mission: Build an inclusive space where connection leads to opportunity and visibility fuels momentum.
How we do it: Peer‑to‑peer support, networking events, and shared learning that open doors to possibilities for learning, connecting, and growing.

Industry – Technology, Information & Internet
Founded – 2025
Specialties – Mentorship, Community Development, Product Management, Design Thinking for AI Experiences, Artificial Intelligence, Technology Leadership, Women in Tech, Women in IT

How You Can Join the Movement

Opportunity	What You’ll Experience
Attend an Interview Session	Live, interactive Q&A with AI leaders—ask anything, from model‑selection tricks to career advice.
Become a Mentee	A tailored mentorship plan that maps your technical goals and personal growth milestones.
Volunteer as a Mentor	Share your expertise, help shape the next wave of women leaders, and expand your own network.
Sponsor or Speak	Showcase your organization’s commitment to diversity and gain visibility among a highly engaged audience.

My Call to Action

If you’re reading this, you already have a voice.
Use it to mentor, to amplify, to sponsor, or simply to listen.
Together, we can transform the AI landscape from a space that talks about inclusion into one that lives it.

Quick Links

LinkedIn WAID Community Hub – Follow this for updates
Luma Online Meetup – Sign up for notifications for our online events.

🎉 Let’s Build a Future Where Every Woman Feels She belongs in AI.

I’m proudly volunteering with Women in AI and Digital, and I invite you to walk this path with me.

Hybrid Platform: A Panel at IBM TechXchange 2025

Wed, 08 Oct 2025 07:30:00 +0000

From Silos to Seamless Flow – Building Hybrid Workflows That Scale

A Personal Note

I was honored to moderate the IBM TechXchange 2025 Peer Roundtable titled “Building Seamless Workflows Across Hybrid Environments.” As an AI consultant and IBM champion I had the pleasure of moderating the conversation, fielding questions, and helping the participants surface practical patterns for integrating on‑prem, cloud, and edge resources into a single, reliable workflow.

My partners in crime were Chris Backer, Madhu Kochar, Steven Perva, and Sarah Julia Kriesch.

Below you’ll find a concise recap of the roundtable insights, followed by a deeper dive into the lessons learned and actionable tactics you can start using today.

📊 Quick‑Take Summary of the Roundtable

What We Explored	Why It Matters	Key Take‑aways for Practitioners
Connecting disparate tools & platforms (on‑prem, cloud, edge)	Breaks silos, reduces manual hand‑offs, unlocks automation.	• Create a single source of truth inventory of services. • Adopt API‑first integration layers. • Use event‑driven patterns (Kafka, IBM Event Streams) for real‑time data flow.
Common setbacks (inconsistent APIs, latency spikes, vendor lock‑in)	Project delays, higher TCO, unpredictable performance.	• Implement contract testing early. • Apply observability stacks (Prometheus, IBM Observability by Instana). • Prefer containerized, stateless services to mitigate lock‑in.
Security & visibility across hybrid landscapes	A breach in one domain can cascade; lack of visibility stalls troubleshooting.	• Deploy Zero‑Trust networking and micro‑segmentation. • Centralize IAM. • Unified logging/SIEM (IBM QRadar) for cross‑environment correlation.
Regulatory & governance pressures	Uncertainty can freeze innovation; clear guidance can accelerate road‑maps.	• Adopt policy‑as‑code. • Map regulations to concrete data‑flow controls and automation rules. • Leverage AI‑driven compliance dashboards for proactive risk detection.
AI‑enhanced workflows (e.g.,with Maximo and IBM watsonx)	Turn data into actionable insight, speed decision‑making, cut manual effort.	• Use a data‑fabric platform to feed trusted AI models. • Start with low‑risk use cases—predictive maintenance, anomaly detection—and expand as confidence grows.

1️⃣ Why Hybrid Integration Is No Longer Optional

Modern enterprises run on a patchwork of on‑premises servers, public clouds, and edge devices. When each environment speaks its own language, moving data becomes costly and error‑prone. The roundtable showed that the first step toward a unified workflow is visibility: catalogue every endpoint, map its data contracts, and treat every interaction as a first‑class API.

Takeaway: A single source of truth for services and contracts eliminates unexpected breakages downstream.

2️⃣ Common Pitfalls & How to Dodge Them

Pitfall	Real‑world Symptom	Remedy (from the discussion)
Inconsistent API contracts	“The integration failed because the vendor changed the schema overnight.”	Adopt contract testing and versioned API gateways.
Latency spikes in cross‑cloud calls	“Requests take >5 s when hitting an external SaaS.”	Move to event‑driven architectures and place compute closer to the data source (edge).
Security blind spots	“We discovered a compromised edge node weeks later.”	Implement Zero‑Trust policies and unify logging with SIEM.
Regulatory uncertainty	“New data‑localization rules forced us to halt a migration.”	Use policy‑as‑code and AI‑enabled compliance dashboards to pre‑emptively adapt.

3️⃣ The Role of AI in Making Workflows “Smart”

AI isn’t a silver bullet, but it turns data into insight that can automate decisions. Participants highlighted three practical entry points, one of which directly ties to the public administration and from the application of Maximo to predictive maintenance:

Predictive Maintenance – Using sensor streams from edge devices to trigger pre‑emptive service calls.
Anomaly Detection – Feeding unified logs into a machine learning model that flags out‑of‑pattern behavior before it becomes an outage.
Workflow Optimisation – Recommending the next best step in an automation chain (e.g., “run job X before job Y”) based on historical success rates.

4️⃣ Governance + Speed: Managing Regulatory Constraints

Regulators often feel like moving finish lines. The conversation on the regulatory hurdles kept was vivid. The roundtable consensus was:

Policy‑as‑Code turns abstract rules into executable checks that run automatically in CI/CD pipelines.
Unified Governance Platforms (for example, watsonx Governance for AI models) provide a single pane of glass for data‑location, retention, and access policies.
AI‑assisted compliance can surface the most urgent gaps, allowing teams to pause or accelerate projects with data‑backed justification rather than guesswork.

5️⃣ Blueprint for a “Seamless Workflow” Initiative

Discover & Map – Catalogue every system, data source, and integration point.
Standardize Contracts – Define OpenAPI specs, versioning rules, and test contracts.
Build Observability – Deploy metrics, tracing, and logs that span environments.
Secure the Path – Apply micro‑segmentation, IAM federation, and data‑masking where needed.
Layer AI Incrementally – Choose a pilot use case (e.g., the email‑reply automation), train models on trusted data, and monitor ROI.
Govern & Iterate – Use policy‑as‑code to keep compliance baked into every release.

6️⃣ Closing Thought

The roundtable proved that speed and safety are not opposites—they become allies when you design integration with visibility, automation, and governance baked in from day one. By treating hybrid environments as a single, programmable fabric, organizations can unlock the agility needed to compete in today’s data‑driven market.

AI for Science

Tue, 21 Jan 2025 00:00:00 +0000

AI‑Enhanced Science: How Generative Models Are Accelerating Discovery, Literature Mining, and Idea Generation
Originally featured on the 

1. AI as a “Hilbert” for Equation Discovery

The most eye‑catching advance comes from the AI‑Hilbert algorithm, whose recent Nature Communications paper demonstrates that multivariate polynomial generators can invent new scientific laws from existing theory and data.

Why it matters

Data‑scarce domains (e.g., high‑energy physics, climate modeling) often lack clean, labeled datasets. Traditional symbolic regression struggles when the search space is huge and the underlying dynamics are noisy.
AI‑Hilbert expands the search space by coupling continuous polynomial families with a Bayesian‑style pruning of implausible terms, delivering equations that are both interpretable and generalizable.

Bottom line – AI can now act as a “virtual mathematician,” surfacing equations that push the frontier of scientific theory while keeping the output human‑readable and testable.

2. Smarter Literature Mining with SciLitLLM

Reading the literature is the backbone of any research program, yet the semantic gap between disciplines hampers existing LLMs. SciLitLLM, a family of models built on a continual‑pre‑training + supervised fine‑tuning pipeline, directly addresses this problem.

Key capabilities

Domain‑aware embeddings that capture jargon from chemistry, biology, nanomaterials, etc., without catastrophic forgetting.
Ability to extract targeted facts (e.g., “list all catalysts reported with >95 % yield under 25 °C”) and produce concise, citation‑ready summaries.
Human‑in‑the‑loop validation layer: researchers verify that hallucinations are filtered before conclusions are drawn.

Limitations – The model is powerful but not a substitute for critical appraisal; it still requires domain experts to curate outputs and guard against subtle misinterpretations.

3. LLM‑Generated Research Ideas (and Their Unexpected Novelty)

A Stanford‑led pre‑print experiment pitted human‑only idea generation against LLM‑generated proposals that were subsequently re‑ranked by expert reviewers.

Result: The top‑ranked LLM ideas were judged significantly more novel than those produced solely by the human panel, even though feasibility scores were comparable.
Implication: Large language models can break cognitive lock‑in, surfacing unconventional connections that traditional pipelines often overlook.
Caveats: Novelty does not guarantee practicality; further validation and feasibility modeling are required before moving to grant proposals or experimental testing.

4. The Common Thread & What Still Needs to Happen

All three examples share a common prerequisite: they are research‑grade tools, not off‑the‑shelf plug‑ins. Realising their full potential demands:

Customization – fine‑tuning on discipline‑specific corpora or data pipelines.
Trust & Transparency – rigorous validation, explainability layers, and community benchmarks.
Institutional Investment – compute resources, training programs, and integration into research workflows.

In short, AI is moving from a supporting calculator to a co‑investigator, but the transition hinges on sustained collaboration between technologists, domain scientists, and research administrators.

Looking Ahead

The convergence of symbolic equation generators, domain‑aware literature models, and ideation‑focused LLMs suggests a new research ecosystem where AI amplifies every stage of the scientific method—from hypothesis birth to experimental validation. When these tools become as routine as a statistical package, we can expect a acceleration of discovery across fields that have traditionally stagnated under data scarcity and human cognitive limits.

Stay tuned to Diagonalising for deeper dives into each tool, practical implementation guides, and interviews with the scientists who are already piloting them.

Artificial Intelligence | Giulia Solinas

Building Agents in Bob with a Software Spec Driven Approach

Building Agents in Bob with a Software Spec Driven Approach

Why Spec Driven Agent Development Matters

The Bob Skill Pipeline

Step 1: Start with solution-architect

Step 2: Convert Architecture into SOPs with sop-builder skills

Step 3: Generate the wxO Solution with wxo-builder skills

Step 4: Audit and Document with wxo-analyzer skills

A Practical End-to-End Flow

Best Practices for Spec Driven Agent Work

What This Changes

Agentic AI

Agentic AI

WAID

Women in AI and Digital — From Career Change to Community

Who I Am & Why I’m Here

What WAID Does (in a nutshell)

How You Can Join the Movement

My Call to Action

Quick Links

🎉 Let’s Build a Future Where Every Woman Feels She belongs in AI.

Hybrid Platform: A Panel at IBM TechXchange 2025

From Silos to Seamless Flow – Building Hybrid Workflows That Scale

A Personal Note

📊 Quick‑Take Summary of the Roundtable

1️⃣ Why Hybrid Integration Is No Longer Optional

2️⃣ Common Pitfalls & How to Dodge Them

3️⃣ The Role of AI in Making Workflows “Smart”

4️⃣ Governance + Speed: Managing Regulatory Constraints

5️⃣ Blueprint for a “Seamless Workflow” Initiative

6️⃣ Closing Thought

AI for Science

1. AI as a “Hilbert” for Equation Discovery

2. Smarter Literature Mining with SciLitLLM

3. LLM‑Generated Research Ideas (and Their Unexpected Novelty)

4. The Common Thread & What Still Needs to Happen

Looking Ahead

Step 1: Start with `solution-architect`

Step 2: Convert Architecture into SOPs with `sop-builder` skills

Step 3: Generate the wxO Solution with `wxo-builder` skills

Step 4: Audit and Document with `wxo-analyzer` skills

Women in AI and Digital — From Career Change to Community

4️⃣ Governance + Speed: Managing Regulatory Constraints

1. AI as a “Hilbert” for Equation Discovery

2. Smarter Literature Mining with SciLitLLM

3. LLM‑Generated Research Ideas (and Their Unexpected Novelty)

4. The Common Thread & What Still Needs to Happen