Look, growing a business isn’t some neat formula you can plug into a spreadsheet. Most of the time you’re winging it, making calls based on half the informationLook, growing a business isn’t some neat formula you can plug into a spreadsheet. Most of the time you’re winging it, making calls based on half the information

How to Grow an Engineering Business: Lessons from Expanding Across New Zealand

Look, growing a business isn’t some neat formula you can plug into a spreadsheet. Most of the time you’re winging it, making calls based on half the information you’d like to have, and hoping things work out.

When the folks at Landmark Consultants pushed into Auckland from Christchurch, they didn’t have a five-year plan or investor pitch decks. They spotted an opening in the market, talked it through over way too many coffees, and basically said “screw it, let’s give it a go.”

That was a few years back. Now they’re juggling residential towers, timber builds, some fairly ambitious infrastructure stuff. Has it all gone smoothly? Hell no. There’ve been expensive mistakes, regulatory headaches, projects that nearly didn’t happen. But they’ve made it work, and the business is still growing.

Abin’s one of the engineers and CEO who made that move happen. Here’s what actually went down, without the corporate polish.

Q: How’d you end up in structural engineering?

Abin: Bit of luck, bit of curiosity. I was always that kid pulling things apart to see how they worked—drove my parents mad. When the earthquakes hit Christchurch back in 2010 and 2011, the whole city had to rebuild. Suddenly engineering wasn’t some abstract thing. It was literally shaping whether buildings would stand or fall next time the ground moved.

I joined Landmark not long after. What I liked about them was they weren’t just rubber-stamping designs. They were actually questioning the old ways—trying base isolators, rethinking how joints should flex, that sort of thing. Got thrown in the deep end pretty fast, which turned out to be the best way to learn.

Q: So why Auckland? That’s a big jump.

Abin: Money talks, right? Auckland’s where most of the construction is happening in New Zealand—probably 60% or more of the country’s activity. The skyline’s constantly changing. New apartment blocks, office buildings, transport stuff. It’s non-stop.

But it’s not just about the volume of work. Auckland’s got different challenges. The soil’s volcanic in places, you’ve got wind off the harbour, building codes are different. And everything moves faster there. Developers are always in a rush.

We’d done well in Christchurch—learned a lot about dealing with challenging conditions—and figured that experience would be valuable in Auckland. The demand for structural engineering Auckland services was clearly growing, and not everyone was delivering the quality developers needed. Turned out we were right, but getting established was harder than expected.

Q: What made it hard?

Abin: Well, three main things tripped us up at the start.

Relationships were brutal. Christchurch is small—you know everyone in the industry. Auckland? You’re nobody. I must’ve had fifty coffees in the first few months, went to every networking thing going, took on smaller jobs just to get our name out there. Trust takes time. Can’t rush it.

Then there’s the bureaucracy. Auckland Council’s consent process is… thorough. Which is fine, they’re doing their job, but it slows everything down. We had to completely redo how we documented projects, add more geotechnical detail, learn all these local requirements. Took us a good six months to get our heads around it properly.

Hiring was the third headache. We needed people who already knew Auckland—its soil conditions, local suppliers, who to call when you hit a problem. Couldn’t just relocate the Christchurch crew. So we recruited hard. University partnerships, headhunting experienced engineers, training people up. It was expensive and time-consuming, but you can’t cut corners on your team.

Q: Tell us about a project that shows what you’re doing up there.

Abin: We’ve got this 28-storey residential tower in Newmarket right now. Client wanted high ceilings, minimal internal columns, and—this is the fun part—a rooftop pool that hangs out over the edge of the building. Oh, and they wanted it done in two years. Sure, no problem!

The site’s on reclaimed land. Soil all over the place in terms of density. Nightmare for foundations. We ran probably a dozen different simulations trying to figure out the best approach. Ended up with bored piles under the central core and raft foundations around the edges. It works, and we didn’t blow the budget, which made everyone happy.

For the main structure we used post-tensioned concrete with a dual-core setup. Handles earthquakes, deals with wind, and the architects got their open floor plans. The cantilevered pool needed custom steel trusses with built-in load sensors. If the wind gets above a certain speed, building management gets an alert. Client loved that bit—makes them look high-tech.

That project’s pretty typical of Auckland work. Big ambitions, tight constraints, need to be clever about it. We’re applying everything we picked up in Christchurch—the kind of thinking we’ve written about before—but adapted to a completely different environment.

Q: You mentioned sensors and simulations. How much does technology actually matter?

Abin: It’s pretty much everything now. We don’t just draw plans anymore. Every project starts in BIM—Building Information Modelling. We can simulate wind loads, earthquake scenarios, even foot traffic patterns, all before anyone breaks ground. Catches problems when they’re cheap to fix. Way better than discovering issues once you’ve got steel in the air.

The really interesting stuff happens after construction though. We’re putting IoT sensors into buildings now. Accelerometers, strain gauges, environmental monitors. They stream data constantly. If something’s settling weird or vibrating unexpectedly, we know about it immediately.

In Auckland that’s critical. A problem in a standalone house is manageable. A problem in a tower with 200 apartments? That’s potentially catastrophic. Technology gives us early warning, which is worth its weight in gold.

Q: How are Auckland clients different from Christchurch ones?

Abin: Auckland clients want statement pieces. Buildings that get attention. And they want it done fast, sustainably, and cheaply. Which is… optimistic.

Christchurch after the quakes was all about safety and meeting code. Get buildings up that won’t fall down. Auckland’s way more competitive. Every developer’s trying to outdo the next one. So they push harder, expect more innovation.

We’re doing loads of timber work now—CLT, glulam, that stuff. It’s renewable, goes up quickly, looks good. Modular construction’s getting big too for affordable housing. And every single project has to hit green building standards these days. No exceptions.

The tricky bit is clients want custom work but they also want it fast. So we’ve had to standardise a lot behind the scenes. Pre-approved connection details, material specs we know work, structural systems we’ve tested. That way we can move quickly without compromising on quality. It’s a balancing act.

Q: What’s next? Where’s the industry heading?

Abin: Mass timber’s going to be huge. We’re working on a mordern office building in Auckland that’s 80% timber. The frame went up in about six weeks. You can’t touch that speed with concrete.

Modular construction’s the other big shift. Factory-built modules that get trucked to site and stacked. It’s faster, generates less waste, quality control’s better. We’re trialling it on a social housing project in Manukau. If the numbers work—and I reckon they will—it could really scale.

And we can’t ignore climate change anymore. We’re designing for sea level rise, extreme weather events, all that stuff. Foundations need to be higher, materials need to handle flooding better, we’re looking at adaptive reuse of older buildings. Engineers have to think decades ahead now, not just years.

For us it’s not just about opening offices in more cities. It’s about expanding what engineering actually means—from just structural safety to environmental impact, community resilience, long-term sustainability. That’s where the work’s going.

Q: Advice for someone trying to grow their business?

Abin: Don’t overthink it. Seriously.

Your existing skills are probably more transferable than you think. Everything I learned dealing with Christchurch’s seismic challenges applied in Auckland—just in different ways. The fundamentals don’t change much.

But stay humble. Every market has its quirks. I thought I had New Zealand engineering sussed. Auckland taught me otherwise pretty quickly. Listen more than you talk, especially at the start.

And relationships matter more than anything else. The best projects happen when architects, engineers, contractors, and clients actually trust each other. That takes time to build. Can’t fake it. Start early, invest properly, and it pays off long-term.

Growth isn’t clean or linear. You make decisions with incomplete information, some things work, some don’t, and you adjust. The technical skills matter—obviously—but they’re not enough. You need market timing, local knowledge, good people, and a bit of luck.

The engineering principles stay constant: do precise work, don’t compromise on safety, keep innovating. But how you apply them changes with every city, client, and project. Figure out what travels well and what needs adapting. Get that right and you’re not just growing revenue—you’re building something that actually lasts.

Markets shift. Regulations change. Technology evolves. But if you keep delivering quality work and treat people decently, opportunities keep showing up. That’s really all there is to it.

Comments
Market Opportunity
LOOK Logo
LOOK Price(LOOK)
$0.01569
$0.01569$0.01569
+5.23%
USD
LOOK (LOOK) Live Price Chart
Disclaimer: The articles reposted on this site are sourced from public platforms and are provided for informational purposes only. They do not necessarily reflect the views of MEXC. All rights remain with the original authors. If you believe any content infringes on third-party rights, please contact service@support.mexc.com for removal. MEXC makes no guarantees regarding the accuracy, completeness, or timeliness of the content and is not responsible for any actions taken based on the information provided. The content does not constitute financial, legal, or other professional advice, nor should it be considered a recommendation or endorsement by MEXC.

You May Also Like

21Shares Launches JitoSOL Staking ETP on Euronext for European Investors

21Shares Launches JitoSOL Staking ETP on Euronext for European Investors

21Shares launches JitoSOL staking ETP on Euronext, offering European investors regulated access to Solana staking rewards with additional yield opportunities.Read
Share
Coinstats2026/01/30 12:53
Digital Asset Infrastructure Firm Talos Raises $45M, Valuation Hits $1.5 Billion

Digital Asset Infrastructure Firm Talos Raises $45M, Valuation Hits $1.5 Billion

Robinhood, Sony and trading firms back Series B extension as institutional crypto trading platform expands into traditional asset tokenization
Share
Blockhead2026/01/30 13:30
Summarize Any Stock’s Earnings Call in Seconds Using FMP API

Summarize Any Stock’s Earnings Call in Seconds Using FMP API

Turn lengthy earnings call transcripts into one-page insights using the Financial Modeling Prep APIPhoto by Bich Tran Earnings calls are packed with insights. They tell you how a company performed, what management expects in the future, and what analysts are worried about. The challenge is that these transcripts often stretch across dozens of pages, making it tough to separate the key takeaways from the noise. With the right tools, you don’t need to spend hours reading every line. By combining the Financial Modeling Prep (FMP) API with Groq’s lightning-fast LLMs, you can transform any earnings call into a concise summary in seconds. The FMP API provides reliable access to complete transcripts, while Groq handles the heavy lifting of distilling them into clear, actionable highlights. In this article, we’ll build a Python workflow that brings these two together. You’ll see how to fetch transcripts for any stock, prepare the text, and instantly generate a one-page summary. Whether you’re tracking Apple, NVIDIA, or your favorite growth stock, the process works the same — fast, accurate, and ready whenever you are. Fetching Earnings Transcripts with FMP API The first step is to pull the raw transcript data. FMP makes this simple with dedicated endpoints for earnings calls. If you want the latest transcripts across the market, you can use the stable endpoint /stable/earning-call-transcript-latest. For a specific stock, the v3 endpoint lets you request transcripts by symbol, quarter, and year using the pattern: https://financialmodelingprep.com/api/v3/earning_call_transcript/{symbol}?quarter={q}&year={y}&apikey=YOUR_API_KEY here’s how you can fetch NVIDIA’s transcript for a given quarter: import requestsAPI_KEY = "your_api_key"symbol = "NVDA"quarter = 2year = 2024url = f"https://financialmodelingprep.com/api/v3/earning_call_transcript/{symbol}?quarter={quarter}&year={year}&apikey={API_KEY}"response = requests.get(url)data = response.json()# Inspect the keysprint(data.keys())# Access transcript contentif "content" in data[0]: transcript_text = data[0]["content"] print(transcript_text[:500]) # preview first 500 characters The response typically includes details like the company symbol, quarter, year, and the full transcript text. If you aren’t sure which quarter to query, the “latest transcripts” endpoint is the quickest way to always stay up to date. Cleaning and Preparing Transcript Data Raw transcripts from the API often include long paragraphs, speaker tags, and formatting artifacts. Before sending them to an LLM, it helps to organize the text into a cleaner structure. Most transcripts follow a pattern: prepared remarks from executives first, followed by a Q&A session with analysts. Separating these sections gives better control when prompting the model. In Python, you can parse the transcript and strip out unnecessary characters. A simple way is to split by markers such as “Operator” or “Question-and-Answer.” Once separated, you can create two blocks — Prepared Remarks and Q&A — that will later be summarized independently. This ensures the model handles each section within context and avoids missing important details. Here’s a small example of how you might start preparing the data: import re# Example: using the transcript_text we fetched earliertext = transcript_text# Remove extra spaces and line breaksclean_text = re.sub(r'\s+', ' ', text).strip()# Split sections (this is a heuristic; real-world transcripts vary slightly)if "Question-and-Answer" in clean_text: prepared, qna = clean_text.split("Question-and-Answer", 1)else: prepared, qna = clean_text, ""print("Prepared Remarks Preview:\n", prepared[:500])print("\nQ&A Preview:\n", qna[:500]) With the transcript cleaned and divided, you’re ready to feed it into Groq’s LLM. Chunking may be necessary if the text is very long. A good approach is to break it into segments of a few thousand tokens, summarize each part, and then merge the summaries in a final pass. Summarizing with Groq LLM Now that the transcript is clean and split into Prepared Remarks and Q&A, we’ll use Groq to generate a crisp one-pager. The idea is simple: summarize each section separately (for focus and accuracy), then synthesize a final brief. Prompt design (concise and factual) Use a short, repeatable template that pushes for neutral, investor-ready language: You are an equity research analyst. Summarize the following earnings call sectionfor {symbol} ({quarter} {year}). Be factual and concise.Return:1) TL;DR (3–5 bullets)2) Results vs. guidance (what improved/worsened)3) Forward outlook (specific statements)4) Risks / watch-outs5) Q&A takeaways (if present)Text:<<<{section_text}>>> Python: calling Groq and getting a clean summary Groq provides an OpenAI-compatible API. Set your GROQ_API_KEY and pick a fast, high-quality model (e.g., a Llama-3.1 70B variant). We’ll write a helper to summarize any text block, then run it for both sections and merge. import osimport textwrapimport requestsGROQ_API_KEY = os.environ.get("GROQ_API_KEY") or "your_groq_api_key"GROQ_BASE_URL = "https://api.groq.com/openai/v1" # OpenAI-compatibleMODEL = "llama-3.1-70b" # choose your preferred Groq modeldef call_groq(prompt, temperature=0.2, max_tokens=1200): url = f"{GROQ_BASE_URL}/chat/completions" headers = { "Authorization": f"Bearer {GROQ_API_KEY}", "Content-Type": "application/json", } payload = { "model": MODEL, "messages": [ {"role": "system", "content": "You are a precise, neutral equity research analyst."}, {"role": "user", "content": prompt}, ], "temperature": temperature, "max_tokens": max_tokens, } r = requests.post(url, headers=headers, json=payload, timeout=60) r.raise_for_status() return r.json()["choices"][0]["message"]["content"].strip()def build_prompt(section_text, symbol, quarter, year): template = """ You are an equity research analyst. Summarize the following earnings call section for {symbol} ({quarter} {year}). Be factual and concise. Return: 1) TL;DR (3–5 bullets) 2) Results vs. guidance (what improved/worsened) 3) Forward outlook (specific statements) 4) Risks / watch-outs 5) Q&A takeaways (if present) Text: <<< {section_text} >>> """ return textwrap.dedent(template).format( symbol=symbol, quarter=quarter, year=year, section_text=section_text )def summarize_section(section_text, symbol="NVDA", quarter="Q2", year="2024"): if not section_text or section_text.strip() == "": return "(No content found for this section.)" prompt = build_prompt(section_text, symbol, quarter, year) return call_groq(prompt)# Example usage with the cleaned splits from Section 3prepared_summary = summarize_section(prepared, symbol="NVDA", quarter="Q2", year="2024")qna_summary = summarize_section(qna, symbol="NVDA", quarter="Q2", year="2024")final_one_pager = f"""# {symbol} Earnings One-Pager — {quarter} {year}## Prepared Remarks — Key Points{prepared_summary}## Q&A Highlights{qna_summary}""".strip()print(final_one_pager[:1200]) # preview Tips that keep quality high: Keep temperature low (≈0.2) for factual tone. If a section is extremely long, chunk at ~5–8k tokens, summarize each chunk with the same prompt, then ask the model to merge chunk summaries into one section summary before producing the final one-pager. If you also fetched headline numbers (EPS/revenue, guidance) earlier, prepend them to the prompt as brief context to help the model anchor on the right outcomes. Building the End-to-End Pipeline At this point, we have all the building blocks: the FMP API to fetch transcripts, a cleaning step to structure the data, and Groq LLM to generate concise summaries. The final step is to connect everything into a single workflow that can take any ticker and return a one-page earnings call summary. The flow looks like this: Input a stock ticker (for example, NVDA). Use FMP to fetch the latest transcript. Clean and split the text into Prepared Remarks and Q&A. Send each section to Groq for summarization. Merge the outputs into a neatly formatted earnings one-pager. Here’s how it comes together in Python: def summarize_earnings_call(symbol, quarter, year, api_key, groq_key): # Step 1: Fetch transcript from FMP url = f"https://financialmodelingprep.com/api/v3/earning_call_transcript/{symbol}?quarter={quarter}&year={year}&apikey={api_key}" resp = requests.get(url) resp.raise_for_status() data = resp.json() if not data or "content" not in data[0]: return f"No transcript found for {symbol} {quarter} {year}" text = data[0]["content"] # Step 2: Clean and split clean_text = re.sub(r'\s+', ' ', text).strip() if "Question-and-Answer" in clean_text: prepared, qna = clean_text.split("Question-and-Answer", 1) else: prepared, qna = clean_text, "" # Step 3: Summarize with Groq prepared_summary = summarize_section(prepared, symbol, quarter, year) qna_summary = summarize_section(qna, symbol, quarter, year) # Step 4: Merge into final one-pager return f"""# {symbol} Earnings One-Pager — {quarter} {year}## Prepared Remarks{prepared_summary}## Q&A Highlights{qna_summary}""".strip()# Example runprint(summarize_earnings_call("NVDA", 2, 2024, API_KEY, GROQ_API_KEY)) With this setup, generating a summary becomes as simple as calling one function with a ticker and date. You can run it inside a notebook, integrate it into a research workflow, or even schedule it to trigger after each new earnings release. Free Stock Market API and Financial Statements API... Conclusion Earnings calls no longer need to feel overwhelming. With the Financial Modeling Prep API, you can instantly access any company’s transcript, and with Groq LLM, you can turn that raw text into a sharp, actionable summary in seconds. This pipeline saves hours of reading and ensures you never miss the key results, guidance, or risks hidden in lengthy remarks. Whether you track tech giants like NVIDIA or smaller growth stocks, the process is the same — fast, reliable, and powered by the flexibility of FMP’s data. Summarize Any Stock’s Earnings Call in Seconds Using FMP API was originally published in Coinmonks on Medium, where people are continuing the conversation by highlighting and responding to this story
Share
Medium2025/09/18 14:40